Sign up to save your podcasts
Or
Share AI Post Transformers
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
AI Post Transformers
By mcgrofTechnology
AI Post Transformers episodes
- Batch-Aware Expert Routing for Faster MoE DecodingThis episode explores a practical systems paper on speeding up Mixture-of-Experts language models at inference time by changing how tokens are routed during decoding, without any retraining. It explains why MoE models, despite using sparse per-token computation, can still be slow in real-world serving because small decode batches activate a large union of different experts, making inference memory-bound due to irregular weight loading. The discussion highlights the paper’s central argument that routing should be batch-aware rather than token-local, so expert choices account for which experts are already being loaded for other tokens in the batch. Listeners would find it interesting for its clear explanation of the gap between MoE’s theoretical efficiency and deployment reality, and for its focus on a low-cost serving optimization with direct economic impact on LLM inference.Sources:1. Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining — Costin-Andrei Oncescu, Qingyang Wu, Wai Tong Chung, Robert Wu, Bryan Gopal, Junxiong Wang, Tri Dao, Ben Athiwaratkun, 2025http://arxiv.org/abs/2511.022372. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer — Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean, 2017https://scholar.google.com/scholar?q=Outrageously+Large+Neural+Networks%3A+The+Sparsely-Gated+Mixture-of-Experts+Layer3. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity — William Fedus, Barret Zoph, Noam Shazeer, 2021https://scholar.google.com/scholar?q=Switch+Transformers%3A+Scaling+to+Trillion+Parameter+Models+with+Simple+and+Efficient+Sparsity4. MegaBlocks: Efficient Sparse Training with Mixture-of-Experts — Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, Yuxiong He and collaborators, 2023https://scholar.google.com/scholar?q=MegaBlocks%3A+Efficient+Sparse+Training+with+Mixture-of-Experts5. Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining — Costin-Andrei Oncescu, Qingyang Wu, Wai Tong Chung, Robert Wu, Bryan Gopal, Junxiong Wang, Tri Dao, Ben Athiwaratkun, 2025https://scholar.google.com/scholar?q=Opportunistic+Expert+Activation%3A+Batch-Aware+Expert+Routing+for+Faster+Decode+Without+Retraining6. Efficient Memory Management for Large Language Model Serving with PagedAttention — Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Hao Zhang, Eric Gonzalez, Ion Stoica, Joseph E. Gonzalez, 2023https://scholar.google.com/scholar?q=Efficient+Memory+Management+for+Large+Language+Model+Serving+with+PagedAttention7. SGLang: Efficient Execution of Structured Language Model Programs — Lianmin Zheng and collaborators, 2024https://scholar.google.com/scholar?q=SGLang%3A+Efficient+Execution+of+Structured+Language+Model+Programs8. DeepSeek-V3 Technical Report — DeepSeek-AI / Liu et al., 2024https://scholar.google.com/scholar?q=DeepSeek-V3+Technical+Report9. Kimi K2 Technical Report — Kimi Team, 2025https://scholar.google.com/scholar?q=Kimi+K2+Technical+Report10. Qwen3 Technical Report — Yang et al., 2025https://scholar.google.com/scholar?q=Qwen3+Technical+Report11. The Roofline Model: A Pedagogical Tool for Program Analysis and Optimization — Samuel Williams, Andrew Waterman, David Patterson, 2009https://scholar.google.com/scholar?q=The+Roofline+Model%3A+A+Pedagogical+Tool+for+Program+Analysis+and+Optimization12. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness — Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, Christopher Ré, 2022https://scholar.google.com/scholar?q=FlashAttention%3A+Fast+and+Memory-Efficient+Exact+Attention+with+IO-Awareness13. Moe-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache — approx. recent systems paper, exact authors unclear from snippet, 2024/2025https://scholar.google.com/scholar?q=Moe-Infinity%3A+Efficient+MoE+Inference+on+Personal+Machines+with+Sparsity-Aware+Expert+Cache14. Diff-MoE: Efficient Batched MoE Inference with Priority-Driven Differential Expert Caching — approx. recent systems paper, exact authors unclear from snippet, 2024/2025https://scholar.google.com/scholar?q=Diff-MoE%3A+Efficient+Batched+MoE+Inference+with+Priority-Driven+Differential+Expert+Caching15. SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference — approx. recent systems paper, exact authors unclear from snippet, 2024/2025https://scholar.google.com/scholar?q=SliceMoE%3A+Bit-Sliced+Expert+Caching+under+Miss-Rate+Constraints+for+Efficient+MoE+Inference16. A Survey on Inference Optimization Techniques for Mixture of Experts Models — approx. recent survey, exact authors unclear from snippet, 2024/2025https://scholar.google.com/scholar?q=A+Survey+on+Inference+Optimization+Techniques+for+Mixture+of+Experts+Models17. Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert Models — approx. recent paper, exact authors unclear from snippet, 2024/2025https://scholar.google.com/scholar?q=Rewiring+Experts+on+the+Fly%3A+Continuous+Rerouting+for+Better+Online+Adaptation+in+Mixture-of-Expert+Models18. Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers — approx. recent paper, exact authors unclear from snippet, 2024/2025https://scholar.google.com/scholar?q=Stabilizing+MoE+Reinforcement+Learning+by+Aligning+Training+and+Inference+Routers19. AI Post Transformers: Switch Transformers: Trillion Parameter Models with Sparsity — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/switch-transformers-trillion-parameter-models-with-sparsity/20. AI Post Transformers: LFM2-8B-A1B: Efficient On-Device Mixture-of-Experts — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/lfm2-8b-a1b-efficient-on-device-mixture-of-experts/21. AI Post Transformers: FlexGen: High-Throughput LLM Inference on a Single GPU — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/flexgen-high-throughput-llm-inference-on-a-single-gpu/22. AI Post Transformers: FlashAttention-2: Faster Attention with Better Parallelism — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/flashattention-2-faster-attention-with-better-parallelism/23. AI Post Transformers: Lookahead Q-Cache for Consistent KV Eviction — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-25-lookahead-q-cache-for-consistent-kv-evic-d97b09.mp324. AI Post Transformers: FAST26: Bidaw: Enhancing Key-Value Caching for Interactive LLM Serving via Bidirectional — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/fast26-bidaw-enhancing-key-value-caching-for-interactive-llm-serving-via-bidirec/Interactive Visualization: Batch-Aware Expert Routing for Faster MoE Decoding0 min
- AI Agent Traps and Prompt InjectionThis episode explores why AI agents become a fundamentally different security problem once language models can browse the web, read email, call tools, store memory, and act inside real software environments. It explains prompt injection as the core boundary failure, showing how webpages, emails, retrieved notes, or API responses can be mistaken for trusted instructions, turning ordinary content into an attack vector with real operational consequences. The discussion then sharpens the distinction between one-off prompt attacks and more systemic failures such as memory poisoning and multi-agent compromise, where corrupted state can persist across sessions or spread through delegated workflows. A listener would find it interesting because it frames agent safety as a concrete systems-security challenge, not just a model-behavior quirk, and clarifies why greater capability also widens the blast radius of failure.Sources:1. AI Agent Traps and Prompt Injection/tmp/submission-source-_s144w4z.txt2. Ignore Previous Prompt: Attack Techniques For Language Models — Fábio Perez, Ian Ribeiro, 2022https://scholar.google.com/scholar?q=Ignore+Previous+Prompt%3A+Attack+Techniques+For+Language+Models3. Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection — Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz, 2023https://scholar.google.com/scholar?q=Not+what+you%27ve+signed+up+for%3A+Compromising+Real-World+LLM-Integrated+Applications+with+Indirect+Prompt+Injection4. Prompt Injection attack against LLM-integrated Applications — Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, Yang Liu, 2023https://scholar.google.com/scholar?q=Prompt+Injection+attack+against+LLM-integrated+Applications5. Prompt Injection Attacks and Defenses in LLM-Integrated Applications — Yupei Liu, Yuqi Jia, Runpeng Geng, Jinyuan Jia, Neil Zhenqiang Gong, 2023https://scholar.google.com/scholar?q=Prompt+Injection+Attacks+and+Defenses+in+LLM-Integrated+Applications6. AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways — Zehang Deng, Yongjian Guo, Changzhou Han, Wanlun Ma, Junwu Xiong, Sheng Wen, Yang Xiang, 2024https://scholar.google.com/scholar?q=AI+Agents+Under+Threat%3A+A+Survey+of+Key+Security+Challenges+and+Future+Pathways7. Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents — Christian Schroeder de Witt, 2025https://scholar.google.com/scholar?q=Open+Challenges+in+Multi-Agent+Security%3A+Towards+Secure+Systems+of+Interacting+AI+Agents8. Red-Teaming LLM Multi-Agent Systems via Communication Attacks — Pengfei He, Yupin Lin, Shen Dong, Han Xu, Yue Xing, Hui Liu, 2025https://scholar.google.com/scholar?q=Red-Teaming+LLM+Multi-Agent+Systems+via+Communication+Attacks9. G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems — Shilong Wang, Guibin Zhang, Miao Yu, Guancheng Wan, Fanci Meng, Chongye Guo, Kun Wang, Yang Wang, 2025https://scholar.google.com/scholar?q=G-Safeguard%3A+A+Topology-Guided+Security+Lens+and+Treatment+on+LLM-based+Multi-agent+Systems10. InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents — Qiusi Zhan, Zhixiang Liang, Zifan Ying, Daniel Kang, 2024https://scholar.google.com/scholar?q=InjecAgent%3A+Benchmarking+Indirect+Prompt+Injections+in+Tool-Integrated+Large+Language+Model+Agents11. Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents — Hanrong Zhang, Jingyuan Huang, Kai Mei, Yifei Yao, Zhenting Wang, Chenlu Zhan, Hongwei Wang, Yongfeng Zhang, 2024https://scholar.google.com/scholar?q=Agent+Security+Bench+%28ASB%29%3A+Formalizing+and+Benchmarking+Attacks+and+Defenses+in+LLM-based+Agents12. AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases — Zhaorun Chen, Zhen Xiang, Chaowei Xiao, Dawn Song, Bo Li, 2024https://scholar.google.com/scholar?q=AgentPoison%3A+Red-teaming+LLM+Agents+via+Poisoning+Memory+or+Knowledge+Bases13. Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems — Donghyun Lee, Mo Tiwari, 2024https://scholar.google.com/scholar?q=Prompt+Infection%3A+LLM-to-LLM+Prompt+Injection+within+Multi-Agent+Systems14. Multi-Agent Systems Execute Arbitrary Malicious Code — Harold Triedman, Rishi D. Jha, Vitaly Shmatikov, 2025https://scholar.google.com/scholar?q=Multi-Agent+Systems+Execute+Arbitrary+Malicious+Code15. Prompt Injection Attacks on Large Language Models: A Survey of Attack Methods, Root Causes, and Defense Strategies — approx. survey by prompt-injection/security researchers, 2025https://scholar.google.com/scholar?q=Prompt+Injection+Attacks+on+Large+Language+Models%3A+A+Survey+of+Attack+Methods%2C+Root+Causes%2C+and+Defense+Strategies16. Prompting for LLM Security and RAG: A Survey from Zero-Shot to Automatic Prompt Optimization (APO) and Prompt-Injection Defenses — approx. security/RAG survey authors, 2025https://scholar.google.com/scholar?q=Prompting+for+LLM+Security+and+RAG%3A+A+Survey+from+Zero-Shot+to+Automatic+Prompt+Optimization+%28APO%29+and+Prompt-Injection+Defenses17. Veriguard: Enhancing LLM Agent Safety via Verified Code Generation — approx. systems/security authors, 2025https://scholar.google.com/scholar?q=Veriguard%3A+Enhancing+LLM+Agent+Safety+via+Verified+Code+Generation18. Enforcement Agents: Enhancing Accountability and Resilience in Multi-Agent AI Frameworks — approx. multi-agent safety authors, 2025https://scholar.google.com/scholar?q=Enforcement+Agents%3A+Enhancing+Accountability+and+Resilience+in+Multi-Agent+AI+Frameworks19. Monitoring LLM-Based Multi-Agent Systems Against Corruptions via Node Evaluation — approx. multi-agent monitoring authors, 2025https://scholar.google.com/scholar?q=Monitoring+LLM-Based+Multi-Agent+Systems+Against+Corruptions+via+Node+Evaluation20. Enhancing Robustness of LLM-Driven Multi-Agent Systems Through Randomized Smoothing — approx. robustness/safety authors, 2025https://scholar.google.com/scholar?q=Enhancing+Robustness+of+LLM-Driven+Multi-Agent+Systems+Through+Randomized+Smoothing21. Assessing and Enhancing the Robustness of LLM-Based Multi-Agent Systems Through Chaos Engineering — approx. systems robustness authors, 2025https://scholar.google.com/scholar?q=Assessing+and+Enhancing+the+Robustness+of+LLM-Based+Multi-Agent+Systems+Through+Chaos+Engineering22. AI Post Transformers: Memory in the Age of AI Agents: Forms, Functions, Dynamics — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-16-memory-in-the-age-of-ai-agents-forms-fun-5abc60.mp323. AI Post Transformers: NeurIPS 2025: Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/neurips-2025-agentic-plan-caching-test-time-memory-for-fast-and-cost-efficient-l/24. AI Post Transformers: ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/reasoningbank-scaling-agent-self-evolving-with-reasoning-memory/25. AI Post Transformers: Qwen3Guard: Streaming Three-Way Safety Classification for LLMs — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-16-qwen3guard-streaming-three-way-safety-cl-26b0ef.mp3Interactive Visualization: AI Agent Traps and Prompt Injection0 min
- Simple Self-Distillation for Better Code GenerationThis episode explores Apple’s paper on whether code models can improve through an extremely simple form of self-distillation: fine-tuning on their own sampled code outputs without using a stronger teacher, execution feedback, verifiers, or reinforcement learning. It situates that idea within the broader history of knowledge distillation and post-training, comparing it to earlier work like Hinton’s distillation, sequence-level distillation, Born Again Networks, Noisy Student, and newer on-policy language model distillation. The discussion focuses on why code generation is a particularly revealing testbed, since benchmarks like pass@1 and pass@k make it easier to tell whether self-distillation is uncovering latent capability or just repackaging errors. A listener would find it interesting because the paper challenges a core assumption in modern model improvement: that meaningful gains require expensive external supervision rather than a surprisingly cheap training loop around the model itself.Sources:1. Embarrassingly Simple Self-Distillation Improves Code Generation — Ruixiang Zhang, Richard He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang, 2026http://arxiv.org/abs/2604.011932. Distilling the Knowledge in a Neural Network — Geoffrey Hinton, Oriol Vinyals, Jeff Dean, 2015https://scholar.google.com/scholar?q=Distilling+the+Knowledge+in+a+Neural+Network3. Sequence-Level Knowledge Distillation — Yoon Kim, Alexander M. Rush, 2016https://scholar.google.com/scholar?q=Sequence-Level+Knowledge+Distillation4. Born Again Neural Networks — Tommaso Furlanello, Zachary Lipton, Michael Tschannen, Laurent Itti, Anima Anandkumar, 2018https://scholar.google.com/scholar?q=Born+Again+Neural+Networks5. Self-training with Noisy Student improves ImageNet classification — Qizhe Xie, Minh-Thang Luong, Eduard Hovy, Quoc V. Le, 2020https://scholar.google.com/scholar?q=Self-training+with+Noisy+Student+improves+ImageNet+classification6. On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes — Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos Garea, Matthieu Geist, Olivier Bachem, 2024https://scholar.google.com/scholar?q=On-Policy+Distillation+of+Language+Models%3A+Learning+from+Self-Generated+Mistakes7. Evaluating Large Language Models Trained on Code — Mark Chen, Jerry Tworek, Heewoo Jun, et al., 2021https://scholar.google.com/scholar?q=Evaluating+Large+Language+Models+Trained+on+Code8. Program Synthesis with Large Language Models — Jacob Austin, Augustus Odena, Maxwell Nye, et al., 2021https://scholar.google.com/scholar?q=Program+Synthesis+with+Large+Language+Models9. Measuring Coding Challenge Competence With APPS — Dan Hendrycks, Collin Burns, Steven Basart, et al., 2021https://scholar.google.com/scholar?q=Measuring+Coding+Challenge+Competence+With+APPS10. Self-Consistency Improves Chain of Thought Reasoning in Language Models — Xuezhi Wang, Jason Wei, Dale Schuurmans, et al., 2022https://scholar.google.com/scholar?q=Self-Consistency+Improves+Chain+of+Thought+Reasoning+in+Language+Models11. DeepSeek-R1 — DeepSeek-AI, 2025https://scholar.google.com/scholar?q=DeepSeek-R112. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code — Prasenjit Jain, et al., 2024https://scholar.google.com/scholar?q=LiveCodeBench%3A+Holistic+and+Contamination+Free+Evaluation+of+Large+Language+Models+for+Code13. SelfCodeAlign: Self-Alignment for Code Generation — Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm de Vries, Leandro von Werra, Arjun Guha, Lingming Zhang, 2024https://scholar.google.com/scholar?q=SelfCodeAlign%3A+Self-Alignment+for+Code+Generation14. Iterative Self-Training for Code Generation via Reinforced Re-Ranking — Nikita Sorokin, Ivan Sedykh, Valentin Malykh, 2025https://scholar.google.com/scholar?q=Iterative+Self-Training+for+Code+Generation+via+Reinforced+Re-Ranking15. On the Role of Temperature Sampling in Test-Time Scaling — Yuheng Wu, Azalia Mirhoseini, Thierry Tambe, 2025https://scholar.google.com/scholar?q=On+the+Role+of+Temperature+Sampling+in+Test-Time+Scaling16. OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement — Tianyu Zheng, Ge Zhang, Tianhao Shen, Xueling Liu, Bill Yuchen Lin, Jie Fu, Wenhu Chen, Xiang Yue, 2024https://scholar.google.com/scholar?q=OpenCodeInterpreter%3A+Integrating+Code+Generation+with+Execution+and+Refinement17. GenX: Mastering Code and Test Generation with Execution Feedback — Nan Wang, Yafei Liu, Chen Chen, Haonan Lu, 2024https://scholar.google.com/scholar?q=GenX%3A+Mastering+Code+and+Test+Generation+with+Execution+Feedback18. InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback — John Yang, Akshara Prabhakar, Karthik Narasimhan, Shunyu Yao, 2023https://scholar.google.com/scholar?q=InterCode%3A+Standardizing+and+Benchmarking+Interactive+Coding+with+Execution+Feedback19. AI Post Transformers: Evolving Language Models Without Labels: EVOL-RL — Hal Turing & Dr. Ada Shannon, Fri,https://podcast.do-not-panic.com/episodes/evolving-language-models-without-labels-evol-rl/20. AI Post Transformers: Lp-Reg: Low-Probability Tokens Sustain RL Exploration — Hal Turing & Dr. Ada Shannon, Sun,https://podcast.do-not-panic.com/episodes/lp-reg-low-probability-tokens-sustain-rl-exploration/21. AI Post Transformers: NeurIPS 2025: SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data — Hal Turing & Dr. Ada Shannon, Sat,https://podcast.do-not-panic.com/episodes/neurips-2025-serl-self-play-reinforcement-learning-for-large-language-models-wit/22. AI Post Transformers: LLM Benchmark Robustness to Linguistic Variation — Hal Turing & Dr. Ada Shannon, Tue,https://podcast.do-not-panic.com/episodes/llm-benchmark-robustness-to-linguistic-variation/Interactive Visualization: Simple Self-Distillation for Better Code Generation0 min
- Emergent Social Risks in Multi-Agent SystemsThis episode explores a paper on how generative multi-agent systems can develop failure modes that do not appear when models are evaluated one at a time. It explains how planner-worker-reviewer loops, negotiation setups, handoff chains, and committee-style aggregation can produce system-level problems such as strategic manipulation, collusion-like behavior, misreporting, conformity, and biased group decisions. The discussion focuses on the paper’s three main risk families: incentive exploitation, collective-cognition failures, and governance breakdowns, while also unpacking the benchmark scenarios used to test those dynamics. Listeners would find it interesting because it connects current real-world agent orchestration patterns to concrete safety and reliability risks, while also probing whether the paper’s evidence is strong enough in light of limited statistics and missing baseline comparisons.Sources:1. Emergent Social Intelligence Risks in Generative Multi-Agent Systems — Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang, 2026http://arxiv.org/abs/2603.277712. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society — Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem, 2023https://scholar.google.com/scholar?q=CAMEL%3A+Communicative+Agents+for+%22Mind%22+Exploration+of+Large+Language+Model+Society3. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation — Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Ahmed Awadallah, Ryen W. White, Doug Burger, Chi Wang, 2024https://scholar.google.com/scholar?q=AutoGen%3A+Enabling+Next-Gen+LLM+Applications+via+Multi-Agent+Conversation4. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework — Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, Jürgen Schmidhuber, 2023https://scholar.google.com/scholar?q=MetaGPT%3A+Meta+Programming+for+A+Multi-Agent+Collaborative+Framework5. Large Language Model based Multi-Agents: A Survey of Progress and Challenges — Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang, 2024https://scholar.google.com/scholar?q=Large+Language+Model+based+Multi-Agents%3A+A+Survey+of+Progress+and+Challenges6. Generative Agents: Interactive Simulacra of Human Behavior — Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein, 2023https://scholar.google.com/scholar?q=Generative+Agents%3A+Interactive+Simulacra+of+Human+Behavior7. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors — Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou, 2023https://scholar.google.com/scholar?q=AgentVerse%3A+Facilitating+Multi-Agent+Collaboration+and+Exploring+Emergent+Behaviors8. Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation — Razan Baltaji, Babak Hemmatian, Lav R. Varshney, 2024https://scholar.google.com/scholar?q=Persona+Inconstancy+in+Multi-Agent+LLM+Collaboration%3A+Conformity%2C+Confabulation%2C+and+Impersonation9. Multi-Agent Risks from Advanced AI — Lewis Hammond, Alan Chan, Jesse Clifton, Jason Hoelscher-Obermaier and many coauthors, 2025https://scholar.google.com/scholar?q=Multi-Agent+Risks+from+Advanced+AI10. Autonomous Algorithmic Collusion: Q-Learning Under Sequential Pricing — Timo Klein, 2019https://scholar.google.com/scholar?q=Autonomous+Algorithmic+Collusion%3A+Q-Learning+Under+Sequential+Pricing11. Artificial Intelligence, Algorithmic Pricing, and Collusion — Emilio Calvano, Giacomo Calzolari, Vincenzo Denicolò, Sergio Pastorello, 2020https://scholar.google.com/scholar?q=Artificial+Intelligence%2C+Algorithmic+Pricing%2C+and+Collusion12. Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions — Ryan Y. Lin, Siddhartha Ojha, Kevin Cai, Maxwell F. Chen, 2024https://scholar.google.com/scholar?q=Strategic+Collusion+of+LLM+Agents%3A+Market+Division+in+Multi-Commodity+Competitions13. AI-Powered Trading, Algorithmic Collusion, and Price Efficiency — Winston Wei Dou, Itay Goldstein, Yan Ji, 2025https://scholar.google.com/scholar?q=AI-Powered+Trading%2C+Algorithmic+Collusion%2C+and+Price+Efficiency14. Emergence of Social Norms in Generative Agent Societies: Principles and Architecture — Siyue Ren, Zhiyao Cui, Ruiqi Song, Zhen Wang, Shuyue Hu, 2024https://scholar.google.com/scholar?q=Emergence+of+Social+Norms+in+Generative+Agent+Societies%3A+Principles+and+Architecture15. Algorithmic Collusion at Test Time: A Meta-game Design and Evaluation — Yuhong Luo, Daniel Schoepflin, Xintong Wang, 2026https://scholar.google.com/scholar?q=Algorithmic+Collusion+at+Test+Time%3A+A+Meta-game+Design+and+Evaluation16. NetSafe: Exploring the Topological Safety of Multi-agent System — Miao Yu et al., 2025https://scholar.google.com/scholar?q=NetSafe%3A+Exploring+the+Topological+Safety+of+Multi-agent+System17. Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs — Marcantonio Bracale Syrnikov et al., 2026https://scholar.google.com/scholar?q=Institutional+AI%3A+Governing+LLM+Collusion+in+Multi-Agent+Cournot+Markets+via+Public+Governance+Graphs18. Verification-Aware Planning for Multi-Agent Systems — Tianyang Xu, Dan Zhang, Kushan Mitra, Estevam Hruschka, 2025https://scholar.google.com/scholar?q=Verification-Aware+Planning+for+Multi-Agent+Systems19. State and Memory is All You Need for Robust and Reliable AI Agents — Matthew Muhoberac et al., 2025https://scholar.google.com/scholar?q=State+and+Memory+is+All+You+Need+for+Robust+and+Reliable+AI+Agents20. AI Post Transformers: Multiagent Debate Improves Language Model Reasoning — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/multiagent-debate-improves-language-model-reasoning/21. AI Post Transformers: Memory in the Age of AI Agents: Forms, Functions, Dynamics — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-16-memory-in-the-age-of-ai-agents-forms-fun-5abc60.mp322. AI Post Transformers: Qwen3Guard: Streaming Three-Way Safety Classification for LLMs — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-16-qwen3guard-streaming-three-way-safety-cl-26b0ef.mp323. AI Post Transformers: Tree-based Group Policy Optimization for LLM Agents — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/tree-based-group-policy-optimization-for-llm-agents/24. AI Post Transformers: Mem0: Scalable Long-Term Memory for AI Agents — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/mem0-scalable-long-term-memory-for-ai-agents/0 min
- Meta-Harness and the Power of LLM PlumbingThis episode explores Meta-Harness, a paper arguing that a large share of LLM system performance comes from the surrounding harness code that manages memory, retrieval, tool use, context formatting, and control flow rather than from model weights alone. It explains how the method uses an outer-loop coding agent to rewrite harness code, inspect raw traces and logs stored on disk, and search for better system designs across tasks like text classification, retrieval-based math reasoning, and agentic coding. The discussion highlights why this matters: in multi-step systems, the same fixed model can perform very differently depending on what information it sees, when it sees it, and how the wrapper code structures the interaction. Listeners would find it interesting because it reframes progress in AI systems as a systems-engineering problem, raising the possibility that better scaffolding around existing models may unlock major gains without retraining the models themselves.Sources:1. Meta-Harness: End-to-End Optimization of Model Harnesses — Yoonho Lee, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, Chelsea Finn, 2026http://arxiv.org/abs/2603.280522. https://yoonholee.com/meta-harness/https://yoonholee.com/meta-harness/3. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines — Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Matei Zaharia, Christopher Potts, and others, 2023https://scholar.google.com/scholar?q=DSPy%3A+Compiling+Declarative+Language+Model+Calls+into+Self-Improving+Pipelines4. Reflexion: Language Agents with Verbal Reinforcement Learning — Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao, 2023https://scholar.google.com/scholar?q=Reflexion%3A+Language+Agents+with+Verbal+Reinforcement+Learning5. MemGPT: Towards LLMs as Operating Systems — Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, Joseph E. Gonzalez, 2023https://scholar.google.com/scholar?q=MemGPT%3A+Towards+LLMs+as+Operating+Systems6. Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models — Qizheng Zhang, Changran Hu, Shubhangi Upasani, Boyuan Ma, Fenglu Hong, James Zou, Kunle Olukotun, and others, 2025https://scholar.google.com/scholar?q=Agentic+Context+Engineering%3A+Evolving+Contexts+for+Self-Improving+Language+Models7. GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — Lakshya A. Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J. Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab, 2025https://scholar.google.com/scholar?q=GEPA%3A+Reflective+Prompt+Evolution+Can+Outperform+Reinforcement+Learning8. TextGrad: Automatic "Differentiation" via Text — Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, James Zou, 2024https://scholar.google.com/scholar?q=TextGrad%3A+Automatic+%22Differentiation%22+via+Text9. Large Language Models as Optimizers — Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, Xinyun Chen, 2023https://scholar.google.com/scholar?q=Large+Language+Models+as+Optimizers10. AlphaEvolve: A Coding Agent for Scientific and Algorithmic Discovery — Alexander Novikov, Ngan Vu, Marvin Eisenberger, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, Sergey Shirobokov, Borislav Kozlovskii, Francisco J. R. Ruiz, Abbas Mehrabian, M. Pawan Kumar, Abigail See, Swarat Chaudhuri, George Holland, Alex Davies, Sebastian Nowozin, Pushmeet Kohli, Matej Balog, 2025https://scholar.google.com/scholar?q=AlphaEvolve%3A+A+Coding+Agent+for+Scientific+and+Algorithmic+Discovery11. Learning to Discover at Test Time — Mert Yuksekgonul, Daniel Koceja, Xinhao Li, Federico Bianchi, Jed McCaleb, Xiaolong Wang, Jan Kautz, Yejin Choi, James Zou, Carlos Guestrin, Yu Sun, 2026https://scholar.google.com/scholar?q=Learning+to+Discover+at+Test+Time12. Grounded Test-Time Adaptation for LLM Agents — Arthur Chen et al., 2025https://scholar.google.com/scholar?q=Grounded+Test-Time+Adaptation+for+LLM+Agents13. Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory — Tianxin Wei et al., 2025https://scholar.google.com/scholar?q=Evo-Memory%3A+Benchmarking+LLM+Agent+Test-time+Learning+with+Self-Evolving+Memory14. M^2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval — Dawei Yan et al., 2026https://scholar.google.com/scholar?q=M%5E2%3A+Dual-Memory+Augmentation+for+Long-Horizon+Web+Agents+via+Trajectory+Summarization+and+Insight+Retrieval15. Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG — Yicheng Zhang et al., 2026https://scholar.google.com/scholar?q=Reinforcement+Fine-Tuning+for+History-Aware+Dense+Retriever+in+RAG16. MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation — Chia-Yuan Chang et al., 2024https://scholar.google.com/scholar?q=MAIN-RAG%3A+Multi-Agent+Filtering+Retrieval-Augmented+Generation17. Fine-tuning with RAG for Improving LLM Learning of New Skills — Humaid Ibrahim, Nikolai Rozanov, Marek Rei, 2025https://scholar.google.com/scholar?q=Fine-tuning+with+RAG+for+Improving+LLM+Learning+of+New+Skills18. AI Post Transformers: Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/agentic-context-engineering-evolving-contexts-for-self-improving-language-models/19. AI Post Transformers: Mem0: Scalable Long-Term Memory for AI Agents — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/mem0-scalable-long-term-memory-for-ai-agents/20. AI Post Transformers: Agentic AI and the Next Intelligence Explosion — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-28-agentic-ai-and-the-next-intelligence-exp-d06561.mp315 min
- OOD Shifts Make LLM Representations SparserThis episode explores a March 19, 2026 study on whether large language models respond to out-of-distribution prompts by compressing their internal activity into fewer active dimensions. It explains how the paper connects two traditions in AI research, mechanistic interpretability and representation geometry, by proposing hidden-state sparsity as a measurable internal signature of stress from harder reasoning tasks, longer contexts, and conflicting information. The discussion breaks down the paper’s core metrics, including Top-k Energy and L1 norm, and clarifies why sparser activations should not be treated as proof of better reasoning or cleaner representations. Listeners would find it interesting because it ties abstract internal model behavior to practical questions about robustness, reliability, and how to evaluate language models beyond just whether their final answers look correct.Sources:1. Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs — Mingyu Jin, Yutong Yin, Jingcheng Niu, Qingcheng Zeng, Wujiang Xu, Mengnan Du, Wei Cheng, Zhaoran Wang, Tianlong Chen, Dimitris N. Metaxas, 2026http://arxiv.org/abs/2603.034152. Domain Generalization: A Survey — Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, Chen Change Loy, 2021https://scholar.google.com/scholar?q=Domain+Generalization%3A+A+Survey3. Invariant Risk Minimization — Martin Arjovsky, Leon Bottou, Ishaan Gulrajani, David Lopez-Paz, 2019https://scholar.google.com/scholar?q=Invariant+Risk+Minimization4. In Search of Lost Domain Generalization — Ishaan Gulrajani, David Lopez-Paz, 2021https://scholar.google.com/scholar?q=In+Search+of+Lost+Domain+Generalization5. WILDS: A Benchmark of in-the-Wild Distribution Shifts — Pang Wei Koh, Shiori Sagawa, Henrik Marklund and many others, 2021https://scholar.google.com/scholar?q=WILDS%3A+A+Benchmark+of+in-the-Wild+Distribution+Shifts6. Emergence of Simple-Cell Receptive Field Properties by Learning a Sparse Code for Natural Images — Bruno A. Olshausen, David J. Field, 1996https://scholar.google.com/scholar?q=Emergence+of+Simple-Cell+Receptive+Field+Properties+by+Learning+a+Sparse+Code+for+Natural+Images7. Deep Sparse Rectifier Neural Networks — Xavier Glorot, Antoine Bordes, Yoshua Bengio, 2011https://scholar.google.com/scholar?q=Deep+Sparse+Rectifier+Neural+Networks8. Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning — Armen Aghajanyan, Sonal Gupta, Luke Zettlemoyer, 2021https://scholar.google.com/scholar?q=Intrinsic+Dimensionality+Explains+the+Effectiveness+of+Language+Model+Fine-Tuning9. Towards Monosemanticity: Decomposing Language Models With Dictionary Learning — Trenton Bricken, Adly Templeton, Joshua Batson and many others, 2023https://scholar.google.com/scholar?q=Towards+Monosemanticity%3A+Decomposing+Language+Models+With+Dictionary+Learning10. Understanding Intermediate Layers Using Linear Classifier Probes — Guillaume Alain, Yoshua Bengio, 2017https://scholar.google.com/scholar?q=Understanding+Intermediate+Layers+Using+Linear+Classifier+Probes11. Deep Contextualized Word Representations — Matthew E. Peters, Mark Neumann, Mohit Iyyer and others, 2018https://scholar.google.com/scholar?q=Deep+Contextualized+Word+Representations12. A Structural Probe for Finding Syntax in Word Representations — John Hewitt, Christopher D. Manning, 2019https://scholar.google.com/scholar?q=A+Structural+Probe+for+Finding+Syntax+in+Word+Representations13. How Contextual Are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings — Kawin Ethayarajh, 2019https://scholar.google.com/scholar?q=How+Contextual+Are+Contextualized+Word+Representations%3F+Comparing+the+Geometry+of+BERT%2C+ELMo%2C+and+GPT-2+Embeddings14. The Geometry of Innocent Flesh on the Bone: Syntactic Structure in Sentence Embeddings — John Hewitt and Christopher D. Manning, 2019https://scholar.google.com/scholar?q=The+Geometry+of+Innocent+Flesh+on+the+Bone%3A+Syntactic+Structure+in+Sentence+Embeddings15. What Factors Affect the Success of In-Context Learning? Investigating the Role of Model Architecture and Task Features — Jason Wei, Yi Tay, Quoc V. Le, Denny Zhou and others, 2022https://scholar.google.com/scholar?q=What+Factors+Affect+the+Success+of+In-Context+Learning%3F+Investigating+the+Role+of+Model+Architecture+and+Task+Features16. Let's Verify Step by Step — Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker and others, 2024https://scholar.google.com/scholar?q=Let%27s+Verify+Step+by+Step17. Do Language Models Generalize to Longer Contexts? — Yixiao Li and collaborators, 2025https://scholar.google.com/scholar?q=Do+Language+Models+Generalize+to+Longer+Contexts%3F18. Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Language Models — Nicola De Cao, Wilker Aziz and Ivan Titov, 2022https://scholar.google.com/scholar?q=Parameter-Efficient+Prompt+Tuning+Makes+Generalized+and+Calibrated+Language+Models19. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks — Jonathan Frankle and Michael Carbin, 2019https://scholar.google.com/scholar?q=The+Lottery+Ticket+Hypothesis%3A+Finding+Sparse%2C+Trainable+Neural+Networks20. Adaptive Mixtures of Local Experts — Robert A. Jacobs, Michael I. Jordan, Steven J. Nowlan and Geoffrey E. Hinton, 1991https://scholar.google.com/scholar?q=Adaptive+Mixtures+of+Local+Experts21. Curriculum Demonstration Selection for In-Context Learning — approx. recent ICL curriculum-learning authors, recenthttps://scholar.google.com/scholar?q=Curriculum+Demonstration+Selection+for+In-Context+Learning22. Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning — approx. recent ICL curriculum-learning authors, recenthttps://scholar.google.com/scholar?q=Let%27s+Learn+Step+by+Step%3A+Enhancing+In-Context+Learning+Ability+with+Curriculum+Learning23. Sparse but not Simpler: A Multi-Level Interpretability Analysis of Vision Transformers — approx. recent interpretability authors, recenthttps://scholar.google.com/scholar?q=Sparse+but+not+Simpler%3A+A+Multi-Level+Interpretability+Analysis+of+Vision+Transformers24. Weight-Sparse Transformers Have Interpretable Circuits — approx. recent mechanistic interpretability authors, recenthttps://scholar.google.com/scholar?q=Weight-Sparse+Transformers+Have+Interpretable+Circuits25. AI Post Transformers: Chain-of-Thought Reasoning: A Brittle Mirage? — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/chain-of-thought-reasoning-a-brittle-mirage/26. AI Post Transformers: Advancing Mechanistic Interpretability with Sparse Autoencoders — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/advancing-mechanistic-interpretability-with-sparse-autoencoders/27. AI Post Transformers: Measuring LLM Reasoning Effort via Deep-Thinking Tokens — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/measuring-llm-reasoning-effort-via-deep-thinking-tokens/28. AI Post Transformers: CLUE: Hidden-State Clustering for Non-parametric Verification — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/clue-hidden-state-clustering-for-non-parametric-verification/29. AI Post Transformers: Inverse IFEval: Unlearning LLM Cognitive Inertia — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/inverse-ifeval-unlearning-llm-cognitive-inertia/30. AI Post Transformers: Hyper-Scaling LLM Inference with KV Cache Compression — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/hyper-scaling-llm-inference-with-kv-cache-compression/23 min
- MetaClaw: Just Talk and Continual Agent AdaptationThis episode takes up the thread from the published episode "MAML and the Basics of Meta-Learning" and shows how those ideas reappear in a much messier setting: a live agent that has to keep improving while it is already deployed. Instead of treating meta-learning as a clean laboratory exercise, the discussion follows MetaClaw as a continual agent system built for changing real workloads, where coding assistants, research agents, and other LLM-based tools face drift in tasks, tools, and failure modes. The hosts frame the paper as a concrete answer to a practical question: how an agent can keep learning on the job rather than waiting for the next full retraining cycle.The conversation focuses on MetaClaw’s two-speed adaptation design. The fast path updates behavior immediately through an external skill library, where failures are distilled into reusable behavioral instructions that can be injected at inference time; the slow path consolidates some of those lessons later through lightweight parameter updates. The hosts unpack the paper’s core formulation of the meta-model as base parameters plus skills, and they explain why that split matters for continual meta-learning: the agent is not only learning facts or storing transcripts, but improving its ability to adapt across a stream of tasks. They also dig into the process reward model, which scores intermediate reasoning and action steps, and the paper’s support-query separation, which keeps skill creation and later reinforcement updates from collapsing into stale self-training.A large part of the episode is about the systems implications of making that loop work in the wild. The hosts examine the paper’s zero-downtime claim in its narrower sense: skill updates can land during live use, while LoRA-based policy optimization is pushed into idle windows detected through sleep schedules, keyboard inactivity, and calendar availability, then swapped back into service later. That makes this episode a useful bridge not only from "MAML and the Basics of Meta-Learning" but, secondarily, from "Doc-to-LoRA: Internalizing Context as LoRA," because the slow adaptation path is explicitly about compressing recurring lessons into lightweight weight changes. The result is a detailed discussion of how MetaClaw tries to turn adaptation into an operational loop rather than a one-shot training event.Sources:1. MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild — Peng Xia, Jianwen Chen, Xinyu Yang, Haoqin Tu, Jiaqi Liu, Kaiwen Xiong, Siwei Han, Shi Qiu, Haonian Ji, Yuyin Zhou, Zeyu Zheng, Cihang Xie, Huaxiu Yao, 2026http://arxiv.org/abs/2603.171872. Reflexion: Language Agents with Verbal Reinforcement Learning — Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao, 2023https://scholar.google.com/scholar?q=Reflexion%3A+Language+Agents+with+Verbal+Reinforcement+Learning3. Voyager: An Open-Ended Embodied Agent with Large Language Models — Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar, 2023https://scholar.google.com/scholar?q=Voyager%3A+An+Open-Ended+Embodied+Agent+with+Large+Language+Models4. ExpeL: LLM Agents Are Experiential Learners — Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, Gao Huang, 2023https://scholar.google.com/scholar?q=ExpeL%3A+LLM+Agents+Are+Experiential+Learners5. Agent Lightning: Train ANY AI Agents with Reinforcement Learning — Xufang Luo, Yuge Zhang, Zhiyuan He, Zilong Wang, Siyun Zhao, Dongsheng Li, Luna K. Qiu, Yuqing Yang, 2025https://scholar.google.com/scholar?q=Agent+Lightning%3A+Train+ANY+AI+Agents+with+Reinforcement+Learning6. ReAct: Synergizing Reasoning and Acting in Language Models — Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao, 2022https://scholar.google.com/scholar?q=ReAct%3A+Synergizing+Reasoning+and+Acting+in+Language+Models7. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks — Chelsea Finn, Pieter Abbeel, Sergey Levine, 2017https://scholar.google.com/scholar?q=Model-Agnostic+Meta-Learning+for+Fast+Adaptation+of+Deep+Networks8. LoRA: Low-Rank Adaptation of Large Language Models — Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, 2021https://scholar.google.com/scholar?q=LoRA%3A+Low-Rank+Adaptation+of+Large+Language+Models9. Who is introducing the failure? Automatically attributing failures of multi-agent systems via spectrum analysis — not verified from snippet, recent (exact year not verified from snippet)https://scholar.google.com/scholar?q=Who+is+introducing+the+failure%3F+Automatically+attributing+failures+of+multi-agent+systems+via+spectrum+analysis10. Weak-to-strong generalization with failure trajectories: A tree-based approach to elicit optimal policy in strong models — not verified from snippet, recent (exact year not verified from snippet)https://scholar.google.com/scholar?q=Weak-to-strong+generalization+with+failure+trajectories%3A+A+tree-based+approach+to+elicit+optimal+policy+in+strong+models11. Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories — not verified from snippet, recent (exact year not verified from snippet)https://scholar.google.com/scholar?q=Understanding+Code+Agent+Behaviour%3A+An+Empirical+Study+of+Success+and+Failure+Trajectories12. Twosome: An efficient online framework to align LLMs with embodied environments via reinforcement learning — not verified from snippet, recent (exact year not verified from snippet)https://scholar.google.com/scholar?q=Twosome%3A+An+efficient+online+framework+to+align+LLMs+with+embodied+environments+via+reinforcement+learning13. AI Post Transformers: MAML and the Basics of Meta-Learning — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-29-maml-and-the-basics-of-meta-learning-7d449f.mp314. AI Post Transformers: Experiential Reinforcement Learning: Internalizing Reflection for Better Policy Training — Hal Turing & Dr. Ada Shannon, Fri,https://podcast.do-not-panic.com/episodes/experiential-reinforcement-learning-internalizing-reflection-for-better-policy-t/15. AI Post Transformers: Mem0: Scalable Long-Term Memory for AI Agents — Hal Turing & Dr. Ada Shannon, Tue,https://podcast.do-not-panic.com/episodes/mem0-scalable-long-term-memory-for-ai-agents/16. AI Post Transformers: NeurIPS 2025: A-Mem: Agentic Memory for LLM Agents — Hal Turing & Dr. Ada Shannon, Sat,https://podcast.do-not-panic.com/episodes/neurips-2025-a-mem-agentic-memory-for-llm-agents/17. AI Post Transformers: Evolving Language Models Without Labels: EVOL-RL — Hal Turing & Dr. Ada Shannon, Fri,https://podcast.do-not-panic.com/episodes/evolving-language-models-without-labels-evol-rl/18. AI Post Transformers: NeurIPS 2025: Reward Reasoning Model — Hal Turing & Dr. Ada Shannon, Sat,https://podcast.do-not-panic.com/episodes/neurips-2025-reward-reasoning-model/19. AI Post Transformers: Generalist Reward Modeling with Inference-Time Scaling — Hal Turing & Dr. Ada Shannon, Tue,https://podcast.do-not-panic.com/episodes/generalist-reward-modeling-with-inference-time-scaling/20. AI Post Transformers: LLM Benchmark Robustness to Linguistic Variation — Hal Turing & Dr. Ada Shannon, Tue,https://podcast.do-not-panic.com/episodes/llm-benchmark-robustness-to-linguistic-variation/Interactive Visualization: MetaClaw: Just Talk and Continual Agent Adaptation0 min
- Doc-to-LoRA: Internalizing Context as LoRAThis episode explores Doc-to-LoRA, a method for turning an entire document into a lightweight LoRA adapter so a language model can answer later questions without repeatedly rereading the source text. It explains how the paper combines context distillation, LoRA fine-tuning, and a Perceiver-style hypernetwork that ingests variable-length documents and emits fixed-size parameter updates, using chunking to handle longer inputs. The discussion highlights reported results such as near-perfect zero-shot performance on synthetic long-context retrieval beyond 32K tokens and improved efficiency on long-document question answering through lower update latency, lower peak memory use, and reduced KV-cache costs at inference time. It also digs into the systems argument behind the work, framing reusable internalized memory as a different primitive from prompting, while questioning how well the approach holds up outside limited-query evaluations and whether its benefits persist against alternatives like prompt compression or keeping context externally.Sources:1. Doc-to-LoRA: Internalizing Context as LoRAhttps://arxiv.org/pdf/2602.159022. 2603.13875https://arxiv.org/abs/2603.138753. 2510.03215https://arxiv.org/abs/2510.032154. LoRA: Low-Rank Adaptation of Large Language Models — Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, 2022https://scholar.google.com/scholar?q=LoRA%3A+Low-Rank+Adaptation+of+Large+Language+Models5. QLoRA: Efficient Finetuning of Quantized LLMs — Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer, 2023https://scholar.google.com/scholar?q=QLoRA%3A+Efficient+Finetuning+of+Quantized+LLMs6. AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning — Qingru Zhang, Minshuo Chen, Alexander Bukharin, Nikos Karampatziakis, Pengcheng He, Yu Cheng, Weizhu Chen, Tuo Zhao, 2023https://scholar.google.com/scholar?q=AdaLoRA%3A+Adaptive+Budget+Allocation+for+Parameter-Efficient+Fine-Tuning7. DoRA: Weight-Decomposed Low-Rank Adaptation — Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Min-Hung Chen, 2024https://scholar.google.com/scholar?q=DoRA%3A+Weight-Decomposed+Low-Rank+Adaptation8. HyperNetworks — David Ha, Andrew Dai, Quoc V. Le, 2016https://scholar.google.com/scholar?q=HyperNetworks9. Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks — Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, James Henderson, 2021https://scholar.google.com/scholar?q=Parameter-efficient+Multi-task+Fine-tuning+for+Transformers+via+Shared+Hypernetworks10. HyperPrompt: Prompt-based Task-Conditioning of Transformers — Yun He, Huaixiu Steven Zheng, Yi Tay, Jai Gupta, Yu Du, Vamsi Aribandi, Zhe Zhao, Yaguang Li, Zhao Chen, Donald Metzler, Heng-Tze Cheng, Ed H. Chi, 2022https://scholar.google.com/scholar?q=HyperPrompt%3A+Prompt-based+Task-Conditioning+of+Transformers11. Doc-to-LoRA: Learning to Instantly Internalize Contexts — Rujikorn Charakorn, Edoardo Cetin, Shinnosuke Uesaka, Robert Tjarko Lange, 2026https://scholar.google.com/scholar?q=Doc-to-LoRA%3A+Learning+to+Instantly+Internalize+Contexts12. Text-to-LoRA: Instant Transformer Adaption — Rujikorn Charakorn, Edoardo Cetin, Yujin Tang, Robert Tjarko Lange, 2025https://scholar.google.com/scholar?q=Text-to-LoRA%3A+Instant+Transformer+Adaption13. Generative Adapter: Contextualizing Language Models in Parameters with a Single Forward Pass — Tianyu Chen, Huanran Fang, Patrick Xia, Xiaodong Liu, Benjamin Van Durme, Luke Zettlemoyer, Jianfeng Gao, Hao Cheng, 2025https://scholar.google.com/scholar?q=Generative+Adapter%3A+Contextualizing+Language+Models+in+Parameters+with+a+Single+Forward+Pass14. Cartridges: Lightweight and General-Purpose Long Context Representations via Self-Study — Sabri Eyuboglu, Ryan Saul Ehrlich, Simran Arora, Neel Guha, Dylan Zinsley, Emily Ruoyu Liu, William Tennien, Atri Rudra, James Zou, Azalia Mirhoseini, Christopher Re, 2025https://scholar.google.com/scholar?q=Cartridges%3A+Lightweight+and+General-Purpose+Long+Context+Representations+via+Self-Study15. Propagating Knowledge Updates to LMs through Distillation — Suchin Padmanabhan, Yoon Kim Onoe, Michael Zhang, Greg Durrett, Eunsol Choi, 2023https://scholar.google.com/scholar?q=Propagating+Knowledge+Updates+to+LMs+through+Distillation16. LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression — Zefan Pan, Qipeng Wu, Hao Jiang, Mengzhou Xia, Xuefei Luo, Jiaqi Zhang, Qingyu Lin, Viktor Ruhle, Yi Yang, Chin-Yew Lin, H. Vicky Zhao, Lidong Qiu, Dongmei Zhang, 2024https://scholar.google.com/scholar?q=LLMLingua-2%3A+Data+Distillation+for+Efficient+and+Faithful+Task-Agnostic+Prompt+Compression17. RazorAttention: Efficient KV Cache Compression Through Retrieval Heads — Hanlin Tang et al., 2024https://scholar.google.com/scholar?q=RazorAttention%3A+Efficient+KV+Cache+Compression+Through+Retrieval+Heads18. Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning — Yu Fu et al., 2024/2025https://scholar.google.com/scholar?q=Not+All+Heads+Matter%3A+A+Head-Level+KV+Cache+Compression+Method+with+Integrated+Retrieval+and+Reasoning19. How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? — Sergey Pletenev et al., 2025https://scholar.google.com/scholar?q=How+Much+Knowledge+Can+You+Pack+into+a+LoRA+Adapter+without+Harming+LLM%3F20. Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation — Yinjie Cheng et al., 2025https://scholar.google.com/scholar?q=Can+Fine-Tuning+Erase+Your+Edits%3F+On+the+Fragile+Coexistence+of+Knowledge+Editing+and+Adaptation21. Memorization in In-Context Learning — Shahriar Golchin et al., 2024https://scholar.google.com/scholar?q=Memorization+in+In-Context+Learning22. In-Context Learning can Perform Continual Learning Like Humans — Liuwang Kang et al., 2025https://scholar.google.com/scholar?q=In-Context+Learning+can+Perform+Continual+Learning+Like+Humans23. AI Post Transformers: LoRA: Low-Rank Adaptation of Large Language Models — Hal Turing & Dr. Ada Shannon, Fri,https://podcast.do-not-panic.com/episodes/lora-low-rank-adaptation-of-large-language-models/24. AI Post Transformers: ShadowKV: High-Throughput Long-Context LLM Inference — Hal Turing & Dr. Ada Shannon, Wed,https://podcast.do-not-panic.com/episodes/shadowkv-high-throughput-long-context-llm-inference/25. AI Post Transformers: Lookahead Q-Cache for Consistent KV Eviction — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-25-lookahead-q-cache-for-consistent-kv-evic-d97b09.mp326. AI Post Transformers: Mem0: Scalable Long-Term Memory for AI Agents — Hal Turing & Dr. Ada Shannon, Tue,https://podcast.do-not-panic.com/episodes/mem0-scalable-long-term-memory-for-ai-agents/27. AI Post Transformers: Kimi Linear: Efficient Expressive Attention Architecture — Hal Turing & Dr. Ada Shannon, Sun,https://podcast.do-not-panic.com/episodes/kimi-linear-efficient-expressive-attention-architecture/28. AI Post Transformers: ComoRAG: Cognitively Inspired Narrative Reasoning — Hal Turing & Dr. Ada Shannon, Tue,https://podcast.do-not-panic.com/episodes/comorag-cognitively-inspired-narrative-reasoning/Interactive Visualization: Doc-to-LoRA: Internalizing Context as LoRA0 min
- MAML and the Basics of Meta-LearningThis episode explores meta-learning through the lens of MAML, explaining how it differs from ordinary supervised learning and standard transfer learning by explicitly training models to adapt quickly to new tasks after just one or a few gradient updates. It walks through the core idea of optimizing for post-update performance, including the role of second-order meta-gradients and the simpler first-order approximation, while placing MAML within the broader landscape of few-shot and gradient-based meta-learning. The discussion also highlights why the paper mattered across multiple domains, covering not just classification benchmarks like Omniglot and MiniImagenet but also regression with sinusoid fitting and reinforcement learning with fast-adapting policies. A listener would find it interesting because it turns a buzzword-heavy area into a concrete framework for thinking about how models can learn to learn, setting up deeper discussions about newer systems built on these ideas.Sources:1. MAML and the Basics of Meta-Learninghttps://arxiv.org/pdf/1703.034002. https://par.nsf.gov/servlets/purl/10427895https://par.nsf.gov/servlets/purl/104278953. Optimization as a Model for Few-Shot Learning — Sachin Ravi, Hugo Larochelle, 2017https://scholar.google.com/scholar?q=Optimization+as+a+Model+for+Few-Shot+Learning4. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks — Chelsea Finn, Pieter Abbeel, Sergey Levine, 2017https://scholar.google.com/scholar?q=Model-Agnostic+Meta-Learning+for+Fast+Adaptation+of+Deep+Networks5. RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning — Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel, 2016https://scholar.google.com/scholar?q=RL%5E2%3A+Fast+Reinforcement+Learning+via+Slow+Reinforcement+Learning6. Meta-Learning in Neural Networks: A Survey — Timothy M. Hospedales, Antreas Antoniou, Paul Micaelli, Amos J. Storkey, 2021https://scholar.google.com/scholar?q=Meta-Learning+in+Neural+Networks%3A+A+Survey7. Matching Networks for One Shot Learning — Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra, 2016https://scholar.google.com/scholar?q=Matching+Networks+for+One+Shot+Learning8. Prototypical Networks for Few-shot Learning — Jake Snell, Kevin Swersky, Richard Zemel, 2017https://scholar.google.com/scholar?q=Prototypical+Networks+for+Few-shot+Learning9. A Closer Look at Few-shot Classification — Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, Jia-Bin Huang, 2019https://scholar.google.com/scholar?q=A+Closer+Look+at+Few-shot+Classification10. Generalizing from a Few Examples — Yaqing Wang, Quanming Yao, James T. Kwok, Lionel M. Ni, 2020https://scholar.google.com/scholar?q=Generalizing+from+a+Few+Examples11. Meta-SGD: Learning to Learn Quickly for Few-Shot Learning — Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li, 2017https://scholar.google.com/scholar?q=Meta-SGD%3A+Learning+to+Learn+Quickly+for+Few-Shot+Learning12. On First-Order Meta-Learning Algorithms — Alex Nichol, Joshua Achiam, John Schulman, 2018https://scholar.google.com/scholar?q=On+First-Order+Meta-Learning+Algorithms13. How to Train Your MAML — Antreas Antoniou, Harrison Edwards, Amos Storkey, 2019https://scholar.google.com/scholar?q=How+to+Train+Your+MAML14. Meta-learning with Differentiable Closed-Form Solvers — Luca Bertinetto, Joao F. Henriques, Philip H. S. Torr, Andrea Vedaldi, 2018https://scholar.google.com/scholar?q=Meta-learning+with+Differentiable+Closed-Form+Solvers15. Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables — Kate Rakelly, Aurick Zhou, Chelsea Finn, Sergey Levine, Deirdre Quillen, 2019https://scholar.google.com/scholar?q=Efficient+Off-Policy+Meta-Reinforcement+Learning+via+Probabilistic+Context+Variables16. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning — Ronald J. Williams, 1992https://scholar.google.com/scholar?q=Simple+Statistical+Gradient-Following+Algorithms+for+Connectionist+Reinforcement+Learning17. Trust Region Policy Optimization — John Schulman, Sergey Levine, Philipp Moritz, Michael Jordan, Pieter Abbeel, 2015https://scholar.google.com/scholar?q=Trust+Region+Policy+Optimization18. Proximal Policy Optimization Algorithms — John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov, 2017https://scholar.google.com/scholar?q=Proximal+Policy+Optimization+Algorithms19. Meta-Learning with Memory-Augmented Neural Networks — Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, Timothy Lillicrap, 2016https://scholar.google.com/scholar?q=Meta-Learning+with+Memory-Augmented+Neural+Networks20. Learning to Learn by Gradient Descent by Gradient Descent — Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Nando de Freitas, 2016https://scholar.google.com/scholar?q=Learning+to+Learn+by+Gradient+Descent+by+Gradient+Descent21. Transformers learn in-context by gradient descent — Johannes von Oswald et al., 2022https://scholar.google.com/scholar?q=Transformers+learn+in-context+by+gradient+descent22. In-context Learning and Gradient Descent Revisited — Gilad Deutch et al., 2023https://scholar.google.com/scholar?q=In-context+Learning+and+Gradient+Descent+Revisited23. Low-Rank Few-Shot Adaptation of Vision-Language Models — Maxime Zanella and Ismail Ben Ayed, 2024https://scholar.google.com/scholar?q=Low-Rank+Few-Shot+Adaptation+of+Vision-Language+Models24. Meta-Adapter: An Online Few-shot Learner for Vision-Language Model — Cheng Cheng et al., 2023https://scholar.google.com/scholar?q=Meta-Adapter%3A+An+Online+Few-shot+Learner+for+Vision-Language+Model25. Cross-Domain Few-Shot Learning via Adaptive Transformer Networks — Naeem Paeedeh et al., 2024https://scholar.google.com/scholar?q=Cross-Domain+Few-Shot+Learning+via+Adaptive+Transformer+Networks26. Few-shot Adaptation of Multi-modal Foundation Models: A Survey — Fan Liu et al., 2024https://scholar.google.com/scholar?q=Few-shot+Adaptation+of+Multi-modal+Foundation+Models%3A+A+Survey27. AI Post Transformers: In-Context Learning as Implicit Learning Algorithms — Hal Turing & Dr. Ada Shannon, Wed,https://podcast.do-not-panic.com/episodes/in-context-learning-as-implicit-learning-algorithms/28. AI Post Transformers: NVIDIA: TTT-E2E: Unlocking Long-Context Learning via End-to-End Test-Time Training — Hal Turing & Dr. Ada Shannon, Sat,https://podcast.do-not-panic.com/episodes/nvidia-ttt-e2e-unlocking-long-context-learning-via-end-to-end-test-time-training/29. AI Post Transformers: Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts — Hal Turing & Dr. Ada Shannon, Tue,https://podcast.do-not-panic.com/episodes/zero-shot-context-generalization-in-reinforcement-learning-from-few-training-con/30. AI Post Transformers: A 2024 Survey Analyzing Generalization in Deep Reinforcement Learning — Hal Turing & Dr. Ada Shannon, Fri,https://podcast.do-not-panic.com/episodes/a-2024-survey-analyzing-generalization-in-deep-reinforcement-learning/Interactive Visualization: MAML and the Basics of Meta-Learning12 min
- Agentic AI and the Next Intelligence ExplosionThis episode explores a perspective paper arguing that the next major leap in AI may come less from scaling a single model and more from organizing intelligence across agents, tools, humans, and institutions. It explains key ideas including agentic AI, multi-agent reasoning, human-AI centaurs, and “societies of thought,” where useful reasoning may emerge through internal dialogue among specialized perspectives rather than just longer single-threaded outputs. The discussion contrasts straightforward parameter scaling with the harder problem of organizational design, emphasizing that collective intelligence only works under specific conditions such as good communication, balanced participation, and careful aggregation. Listeners would find it interesting because it reframes the usual singularity story into a concrete debate about coordination, role design, and whether intelligence scales socially as much as technically.Sources:1. Agentic AI and the next intelligence explosion — James Evans, Benjamin Bratton, Blaise Agüera y Arcas, 2026http://arxiv.org/abs/2603.206392. Evidence for a Collective Intelligence Factor in the Performance of Human Groups — Anita Williams Woolley, Christopher F. Chabris, Alex Pentland, Nada Hashmi, Thomas W. Malone, 2010https://scholar.google.com/scholar?q=Evidence+for+a+Collective+Intelligence+Factor+in+the+Performance+of+Human+Groups3. AI-enhanced Collective Intelligence — Hao Cui, Taha Yasseri, 2024https://scholar.google.com/scholar?q=AI-enhanced+Collective+Intelligence4. Artificial Intelligence for Collective Intelligence: a National-scale Research Strategy — Seth Bullock and many coauthors, 2024https://scholar.google.com/scholar?q=Artificial+Intelligence+for+Collective+Intelligence%3A+a+National-scale+Research+Strategy5. Artificial Intelligence versus Collective Intelligence — Harry Halpin, 2025https://scholar.google.com/scholar?q=Artificial+Intelligence+versus+Collective+Intelligence6. Man-Computer Symbiosis — J. C. R. Licklider, 1960https://scholar.google.com/scholar?q=Man-Computer+Symbiosis7. Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of AI on Knowledge Worker Productivity and Quality — Fabrizio Dell'Acqua, Edward McFowland III, Ethan Mollick, Hila Lifshitz-Assaf, Katherine C. Kellogg, Saran Rajendran, Lisa Krayer, Francois Candelon, Karim R. Lakhani, 2023https://scholar.google.com/scholar?q=Navigating+the+Jagged+Technological+Frontier%3A+Field+Experimental+Evidence+of+the+Effects+of+AI+on+Knowledge+Worker+Productivity+and+Quality8. When Combinations of Humans and AI are Useful: A Systematic Review and Meta-analysis — Michelle Vaccaro, Abdullah Almaatouq, Thomas W. Malone, 2024https://scholar.google.com/scholar?q=When+Combinations+of+Humans+and+AI+are+Useful%3A+A+Systematic+Review+and+Meta-analysis9. Effective Generative AI: The Human-Algorithm Centaur — Soroush Saghafian, Lihi Idan, 2024https://scholar.google.com/scholar?q=Effective+Generative+AI%3A+The+Human-Algorithm+Centaur10. Reasoning Models Generate Societies of Thought — Junsol Kim, Shiyang Lai, Nino Scherrer, Blaise Aguera y Arcas, James Evans, 2026https://scholar.google.com/scholar?q=Reasoning+Models+Generate+Societies+of+Thought11. Self-Consistency Improves Chain of Thought Reasoning in Language Models — Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, Denny Zhou, 2022https://scholar.google.com/scholar?q=Self-Consistency+Improves+Chain+of+Thought+Reasoning+in+Language+Models12. Improving Factuality and Reasoning in Language Models through Multiagent Debate — Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, Igor Mordatch, 2024https://scholar.google.com/scholar?q=Improving+Factuality+and+Reasoning+in+Language+Models+through+Multiagent+Debate13. DeepSeek-R1 Incentivizes Reasoning in LLMs through Reinforcement Learning — Daya Guo and many coauthors, 2025https://scholar.google.com/scholar?q=DeepSeek-R1+Incentivizes+Reasoning+in+LLMs+through+Reinforcement+Learning14. CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society — Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem, 2023https://scholar.google.com/scholar?q=CAMEL%3A+Communicative+Agents+for+%22Mind%22+Exploration+of+Large+Scale+Language+Model+Society15. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation — Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W. White, Doug Burger, Chi Wang, 2024https://scholar.google.com/scholar?q=AutoGen%3A+Enabling+Next-Gen+LLM+Applications+via+Multi-Agent+Conversation16. A Survey on LLM-based Multi-agent Systems: Workflow, Infrastructure, and Challenges — Xinyi Li, Sai Wang, Siqi Zeng, Yu Wu, Yi Yang, 2024https://scholar.google.com/scholar?q=A+Survey+on+LLM-based+Multi-agent+Systems%3A+Workflow%2C+Infrastructure%2C+and+Challenges17. Deep Reinforcement Learning from Human Preferences — P. F. Christiano et al., 2017https://scholar.google.com/scholar?q=Deep+Reinforcement+Learning+from+Human+Preferences18. Constitutional AI: Harmlessness from AI Feedback — Y. Bai et al., 2022https://scholar.google.com/scholar?q=Constitutional+AI%3A+Harmlessness+from+AI+Feedback19. Large AI Models Are Cultural and Social Technologies — H. Farrell, A. Gopnik, C. Shalizi, J. Evans, 2025https://scholar.google.com/scholar?q=Large+AI+Models+Are+Cultural+and+Social+Technologies20. Governing the Commons: The Evolution of Institutions for Collective Action — E. Ostrom, 1990https://scholar.google.com/scholar?q=Governing+the+Commons%3A+The+Evolution+of+Institutions+for+Collective+Action21. Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them — Mirac Suzgun, Nathan Scales, Nathanael Scharli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V. Le, Ed H. Chi, Denny Zhou, Jason Wei, 2022https://scholar.google.com/scholar?q=Challenging+BIG-Bench+Tasks+and+Whether+Chain-of-Thought+Can+Solve+Them22. SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning — Yige Xu, Xu Guo, Zhiwei Zeng, Chunyan Miao, 2025https://scholar.google.com/scholar?q=SoftCoT%2B%2B%3A+Test-Time+Scaling+with+Soft+Chain-of-Thought+Reasoning23. Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning — Chengqi Lyu, Songyang Gao, Yuzhe Gu, Wenwei Zhang, Jianfei Gao and others, 2025https://scholar.google.com/scholar?q=Exploring+the+Limit+of+Outcome+Reward+for+Learning+Mathematical+Reasoning24. Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning — Zheng Zhang, Ziwei Shan, Kaitao Song, Yexin Li, Kan Ren, 2025https://scholar.google.com/scholar?q=Linking+Process+to+Outcome%3A+Conditional+Reward+Modeling+for+LLM+Reasoning25. SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward — Kaixuan Fan, Kaituo Feng, Haoming Lyu, Dongzhan Zhou, Xiangyu Yue, 2025https://scholar.google.com/scholar?q=SophiaVL-R1%3A+Reinforcing+MLLMs+Reasoning+with+Thinking+Reward26. Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions — Eric Zelikman, Qian Huang and others, 2022https://scholar.google.com/scholar?q=Parsel%3A+Algorithmic+Reasoning+with+Language+Models+by+Composing+Decompositions27. Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning — Haozhe Wang, Qixin Xu, Che Liu, Junhong Wu, Fangzhen Lin, Wenhu Chen, 2025https://scholar.google.com/scholar?q=Emergent+Hierarchical+Reasoning+in+LLMs+through+Reinforcement+Learning28. Debate4MATH: Multi-Agent Debate for Fine-Grained Reasoning in Math — Shaowei Zhang, Deyi Xiong, 2025https://scholar.google.com/scholar?q=Debate4MATH%3A+Multi-Agent+Debate+for+Fine-Grained+Reasoning+in+Math29. Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System — Haotian Wang, Xiyuan Du, Weijiang Yu, Qianglong Chen, Kun Zhu, Zheng Chu, Lian Yan, Yi Guan, 2025https://scholar.google.com/scholar?q=Learning+to+Break%3A+Knowledge-Enhanced+Reasoning+in+Multi-Agent+Debate+System30. AI Post Transformers: Reasoning Models Generate Societies of Thought — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/reasoning-models-generate-societies-of-thought/31. AI Post Transformers: HyperAgents and Metacognitive Self-Improvement — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-26-hyperagents-and-metacognitive-self-impro-de711a.mp332. AI Post Transformers: Bloom: an open source tool for automated behavioral evaluations — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/bloom-an-open-source-tool-for-automated-behavioral-evaluations/33. AI Post Transformers: NeurIPS 2025: Reward Reasoning Model — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/neurips-2025-reward-reasoning-model/34. AI Post Transformers: MASA: Meta-Awareness via Self-Alignment Reinforcement Learning — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/masa-meta-awareness-via-self-alignment-reinforcement-learning/35. AI Post Transformers: Evolving Language Models Without Labels: EVOL-RL — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/evolving-language-models-without-labels-evol-rl/36. AI Post Transformers: LeCun's AMI Energy-Based Models and the Path to Autonomous Intelligence — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/lecuns-ami-energy-based-models-and-the-path-to-autonomous-intelligence/Interactive Visualization: Agentic AI and the Next Intelligence Explosion0 min
About AI Post Transformers
From the publisher's feed
AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis,…
proper citations, and nerdy humor.