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
- Explicit Information Transmission for Context CompressionThis episode explores a paper on long-context compression that argues standard “soft compression” methods, which rely on learned memory or gist tokens, lose information because those tokens get overwritten across layers and fail to coordinate what each slot should retain. It explains the paper’s alternative design, which keeps the language model backbone frozen and instead explicitly transmits information from hidden states into a small set of latent slots through a two-stage process: selecting useful signals across layers, then globally allocating token information to slots with a transport-based assignment. The discussion highlights why this matters for deployment, where long contexts and growing KV caches make inference expensive, while also noting the risks of latent compression for exact recall, citations, and fine-grained factual detail. Listeners would find it interesting for both the strong benchmark results, where the method substantially outperforms prior compressors on several QA datasets, and the debate over whether those gains on a 512-token testbed really translate to the much larger context problems practitioners care about.Sources:1. Context Compression via Explicit Information Transmission — Jiangnan Ye, Hanqi Yan, Zhenyi Shen, Heng Chang, Ye Mao, Yulan He, 2026http://arxiv.org/abs/2602.037842. Compressive Transformers for Long-Range Sequence Modelling — Jack W. Rae, Anna Potapenko, Siddhant M. Jayakumar, Timothy P. Lillicrap, 2019https://scholar.google.com/scholar?q=Compressive+Transformers+for+Long-Range+Sequence+Modelling3. Learning to Compress Prompts with Gist Tokens — Jesse Mu, Xiang Lisa Li, Noah D. Goodman, 2023https://scholar.google.com/scholar?q=Learning+to+Compress+Prompts+with+Gist+Tokens4. Adapting Language Models to Compress Contexts — Alexis Chevalier, Alexander Wettig, Anirudh Ajith, Danqi Chen, 2023https://scholar.google.com/scholar?q=Adapting+Language+Models+to+Compress+Contexts5. A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression — Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Xinting Huang, Dong Yu, Zhicheng Dou, 2024https://scholar.google.com/scholar?q=A+Silver+Bullet+or+a+Compromise+for+Full+Attention%3F+A+Comprehensive+Study+of+Gist+Token-based+Context+Compression6. In-context Autoencoder for Context Compression in a Large Language Model — Tao Ge, Jing Hu, Haixun Wang, Si-Qing Chen, Furu Wei, 2024https://scholar.google.com/scholar?q=In-context+Autoencoder+for+Context+Compression+in+a+Large+Language+Model7. 500xCompressor: Generalized Prompt Compression for Large Language Models — Zongqian Li, Yixuan Su, Nigel Collier, 2025https://scholar.google.com/scholar?q=500xCompressor%3A+Generalized+Prompt+Compression+for+Large+Language+Models8. Long Context Compression with Activation Beacon — Peitian Zhang, Zheng Liu, Shitao Xiao, Ninglu Shao, Qiwei Ye, Zhicheng Dou, 2025https://scholar.google.com/scholar?q=Long+Context+Compression+with+Activation+Beacon9. RazorAttention: Efficient KV Cache Compression through Retrieval Heads — approx. anonymous/unknown from snippet, 2025/2026https://scholar.google.com/scholar?q=RazorAttention%3A+Efficient+KV+Cache+Compression+through+Retrieval+Heads10. Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning — approx. anonymous/unknown from snippet, 2025/2026https://scholar.google.com/scholar?q=Not+All+Heads+Matter%3A+A+Head-Level+KV+Cache+Compression+Method+with+Integrated+Retrieval+and+Reasoning11. Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k — approx. anonymous/unknown from snippet, 2025/2026https://scholar.google.com/scholar?q=Efficient+Context+Selection+for+Long-Context+QA%3A+No+Tuning%2C+No+Iteration%2C+Just+Adaptive-k12. TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection — approx. anonymous/unknown from snippet, 2025/2026https://scholar.google.com/scholar?q=TokenSelect%3A+Efficient+Long-Context+Inference+and+Length+Extrapolation+for+LLMs+via+Dynamic+Token-Level+KV+Cache+Selection13. Generative Adapter: Contextualizing Language Models in Parameters with a Single Forward Pass — approx. anonymous/unknown from snippet, 2025/2026https://scholar.google.com/scholar?q=Generative+Adapter%3A+Contextualizing+Language+Models+in+Parameters+with+a+Single+Forward+Pass14. Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning — approx. anonymous/unknown from snippet, 2025/2026https://scholar.google.com/scholar?q=Demystifying+the+Roles+of+LLM+Layers+in+Retrieval%2C+Knowledge%2C+and+Reasoning15. AI Post Transformers: DeepSeek-V4 and Practical Million-Token Context — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-25-deepseek-v4-and-practical-million-token-6f4de1.mp316. AI Post Transformers: Gated Linear Attention for Efficient Long Sequences — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-18-gated-linear-attention-for-efficient-lon-c858ab.mp317. AI Post Transformers: Doc-to-LoRA: Internalizing Context as LoRA — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-29-doc-to-lora-internalizing-context-as-lor-8dd5ec.mp318. AI Post Transformers: Memory Sparse Attention for 100M-Token Scaling — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-07-memory-sparse-attention-for-100m-token-s-377cff.mp319. AI Post Transformers: Recursive Language Models for Arbitrarily Long Prompts — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-recursive-language-models-for-arbitraril-fbcd1c.mp320. AI Post Transformers: How Induction Heads Emerge in Transformers — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-05-03-how-induction-heads-emerge-in-transforme-a7bfcb.mp3Interactive Visualization: Explicit Information Transmission for Context Compression0 min
- Why LLM Serving Needs Mathematical OptimizationThis episode explores a position paper arguing that modern LLM serving has outgrown simple heuristics like FIFO, shortest-queue routing, and LRU eviction. It explains why transformer inference creates harder control problems than standard inference, focusing on continuous batching, KV-cache growth, and the tension between compute-heavy prefill and memory-bound decode phases. The discussion highlights the paper’s central claim that serving systems need explicit objective-driven optimization for routing, admission control, scheduling, and cache management, while also questioning where formal methods would truly outperform today’s stronger heuristic baselines such as vLLM and PagedAttention-inspired designs. Listeners would find it interesting because it connects low-level serving mechanics to real product tradeoffs like latency, throughput, and cache churn, showing why infrastructure choices increasingly shape LLM performance.Sources:1. Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics — Zijie Zhou, 2026http://arxiv.org/abs/2605.012802. PREBLE: Efficient Distributed Prompt Scheduling for LLM Serving — Vikranth Srivatsa, Zijian He, Reyna Abhyankar, Dongming Li, Yiying Zhang, 2024https://scholar.google.com/scholar?q=PREBLE%3A+Efficient+Distributed+Prompt+Scheduling+for+LLM+Serving3. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving — Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, Hao Zhang, 2024https://scholar.google.com/scholar?q=DistServe%3A+Disaggregating+Prefill+and+Decoding+for+Goodput-optimized+Large+Language+Model+Serving4. Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation — Xutong Liu, Baran Atalar, Xiangxiang Dai, Jinhang Zuo, Siwei Wang, John C. S. Lui, Wei Chen, Carlee Joe-Wong, 2026https://scholar.google.com/scholar?q=Semantic+Caching+for+Low-Cost+LLM+Serving%3A+From+Offline+Learning+to+Online+Adaptation5. POLAR: Online Learning for LoRA Adapter Caching and Routing in Edge LLM Serving — Shaoang Li, Jian Li, 2026https://scholar.google.com/scholar?q=POLAR%3A+Online+Learning+for+LoRA+Adapter+Caching+and+Routing+in+Edge+LLM+Serving6. Orca: A Distributed Serving System for Transformer-Based Generative Models — Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, Byung-Gon Chun, 2022https://scholar.google.com/scholar?q=Orca%3A+A+Distributed+Serving+System+for+Transformer-Based+Generative+Models7. Efficient Memory Management for Large Language Model Serving with PagedAttention — Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, Ion Stoica, 2023https://scholar.google.com/scholar?q=Efficient+Memory+Management+for+Large+Language+Model+Serving+with+PagedAttention8. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve — Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, Ramachandran Ramjee, 2024https://scholar.google.com/scholar?q=Taming+Throughput-Latency+Tradeoff+in+LLM+Inference+with+Sarathi-Serve9. SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills — Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, 2023https://scholar.google.com/scholar?q=SARATHI%3A+Efficient+LLM+Inference+by+Piggybacking+Decodes+with+Chunked+Prefills10. Faster LLM Inference using DBMS-Inspired Preemption and Cache Replacement Policies — Kyoungmin Kim, Jiacheng Li, Kijae Hong, Anastasia Ailamaki, 2024https://scholar.google.com/scholar?q=Faster+LLM+Inference+using+DBMS-Inspired+Preemption+and+Cache+Replacement+Policies11. DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving — Ying Yuan et al., 2026https://scholar.google.com/scholar?q=DualMap%3A+Enabling+Both+Cache+Affinity+and+Load+Balancing+for+Distributed+LLM+Serving12. Slice-Level Scheduling for High Throughput and Load Balanced LLM Serving — Ke Cheng et al., 2024https://scholar.google.com/scholar?q=Slice-Level+Scheduling+for+High+Throughput+and+Load+Balanced+LLM+Serving13. A Predictive and Synergistic Two-Layer Scheduling Framework for LLM Serving — Yue Zhang et al., 2025https://scholar.google.com/scholar?q=A+Predictive+and+Synergistic+Two-Layer+Scheduling+Framework+for+LLM+Serving14. KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse — Jingbo Yang et al., 2025https://scholar.google.com/scholar?q=KVLink%3A+Accelerating+Large+Language+Models+via+Efficient+KV+Cache+Reuse15. HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse — Yuwei An et al., 2025https://scholar.google.com/scholar?q=HyperRAG%3A+Enhancing+Quality-Efficiency+Tradeoffs+in+Retrieval-Augmented+Generation+with+Reranker+KV-Cache+Reuse16. ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation — Shihao Wang et al., 2026https://scholar.google.com/scholar?q=ProphetKV%3A+User-Query-Driven+Selective+Recomputation+for+Efficient+KV+Cache+Reuse+in+Retrieval-Augmented+Generation17. dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving — Bingyang Wu et al., 2024https://scholar.google.com/scholar?q=dLoRA%3A+Dynamically+Orchestrating+Requests+and+Adapters+for+LoRA+LLM+Serving18. SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference — Hengrui Zhang et al., 2025https://scholar.google.com/scholar?q=SPAD%3A+Specialized+Prefill+and+Decode+Hardware+for+Disaggregated+LLM+Inference19. AI Post Transformers: Speculative Decoding in Real vLLM Serving — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-speculative-decoding-in-real-vllm-servin-6f4e2b.mp320. 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.mp321. AI Post Transformers: LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-25-lookaheadkv-fast-and-accurate-kv-9cfc9f.mp322. AI Post Transformers: KV Cache TTL for Multi-Turn Agent Scheduling — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-09-kv-cache-ttl-for-multi-turn-agent-schedu-996bf1.mp323. AI Post Transformers: CacheFlow and 3D-Parallel KV Cache Restoration — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-05-01-cacheflow-and-3d-parallel-kv-cache-resto-8db883.mp324. AI Post Transformers: ContiguousKV for Faster LLM Prefill KV Reuse — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-20-contiguouskv-for-faster-llm-prefill-kv-r-59f545.mp325. AI Post Transformers: Breaking the Prefix Barrier with Shared KV Cache — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-24-breaking-the-prefix-barrier-with-shared-a5e5a6.mp326. AI Post Transformers: TokenDance for Multi-Agent KV Cache Sharing — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-22-tokendance-for-multi-agent-kv-cache-shar-aa9b99.mp327. AI Post Transformers: RetrievalAttention for Long-Context LLM Inference — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-17-retrievalattention-for-long-context-llm-ddf566.mp328. AI Post Transformers: KVSwap for Disk-Aware Long-Context On-Device Inference — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-16-kvswap-for-disk-aware-long-context-on-de-f3c15e.mp3Interactive Visualization: Why LLM Serving Needs Mathematical Optimization11 min
- EverMemOS for Long-Horizon Agent MemoryThis episode explores EverMemOS, a memory system for long-lived AI agents that tries to organize past interactions into structured, higher-level semantic “scenes” instead of relying on flat retrieval alone. It explains why bigger context windows and standard RAG often fail when agents accumulate stale preferences, conflicting facts, and fragmented conversational traces, arguing that the real problem is not just forgetting but poorly organized remembering. The discussion walks through the paper’s core design, including MemCells, MemScenes, semantic consolidation, and reconstructive recollection, framing the system as a state-management layer around transformers rather than a new model architecture. A listener would find it interesting because it connects abstract memory research to practical agent failures and offers a concrete alternative for building assistants that can reason more reliably over long time horizons.Sources:1. EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning — Chuanrui Hu, Xingze Gao, Zuyi Zhou, Dannong Xu, Yi Bai, Xintong Li, Hui Zhang, Tong Li, Chong Zhang, Lidong Bing, Yafeng Deng, 2026http://arxiv.org/abs/2601.021632. MemoryBank: Enhancing Large Language Models with Long-Term Memory — Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, Yanlin Wang, 2023https://scholar.google.com/scholar?q=MemoryBank%3A+Enhancing+Large+Language+Models+with+Long-Term+Memory3. MemGPT: Towards LLMs as Operating Systems — Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Joseph E. Gonzalez, 2023https://scholar.google.com/scholar?q=MemGPT%3A+Towards+LLMs+as+Operating+Systems4. A Survey on the Memory Mechanism of Large Language Model based Agents — Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, Ji-Rong Wen, 2024https://scholar.google.com/scholar?q=A+Survey+on+the+Memory+Mechanism+of+Large+Language+Model+based+Agents5. MemOS: A Memory OS for AI System — Zhiyu Li, Shichao Song, Chenyang Xi, Hanyu Wang, Chen Tang, Simin Niu, Ding Chen, et al., 2025https://scholar.google.com/scholar?q=MemOS%3A+A+Memory+OS+for+AI+System6. Memory OS of AI Agent — Jiazheng Kang, Mingming Ji, Zhe Zhao, Ting Bai, 2025https://scholar.google.com/scholar?q=Memory+OS+of+AI+Agent7. Zep: A Temporal Knowledge Graph Architecture for Agent Memory — Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, Daniel Chalef, 2025https://scholar.google.com/scholar?q=Zep%3A+A+Temporal+Knowledge+Graph+Architecture+for+Agent+Memory8. Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory — Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, Deshraj Yadav, 2025https://scholar.google.com/scholar?q=Mem0%3A+Building+Production-Ready+AI+Agents+with+Scalable+Long-Term+Memory9. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory — Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, Dong Yu, 2024https://scholar.google.com/scholar?q=LongMemEval%3A+Benchmarking+Chat+Assistants+on+Long-Term+Interactive+Memory10. Evaluating Very Long-Term Conversational Memory of LLM Agents — Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, Yuwei Fang, 2024https://scholar.google.com/scholar?q=Evaluating+Very+Long-Term+Conversational+Memory+of+LLM+Agents11. BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack — Yuri/Yurii Kuratov et al., 2024https://scholar.google.com/scholar?q=BABILong%3A+Testing+the+Limits+of+LLMs+with+Long+Context+Reasoning-in-a-Haystack12. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks — Yushi Bai et al., 2024/2025https://scholar.google.com/scholar?q=LongBench+v2%3A+Towards+Deeper+Understanding+and+Reasoning+on+Realistic+Long-context+Multitasks13. Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering — Yuelyu Ji, Rui Meng, Zhuochun Li, Daqing He, 2025https://scholar.google.com/scholar?q=Memory-Aware+and+Uncertainty-Guided+Retrieval+for+Multi-Hop+Question+Answering14. BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression — Yuankai Li, Jia-Chen Gu, Di Wu, Kai-Wei Chang, Nanyun Peng, 2024/2025https://scholar.google.com/scholar?q=BRIEF%3A+Bridging+Retrieval+and+Inference+for+Multi-hop+Reasoning+via+Compression15. Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information — Zeyu Zhang et al., 2025https://scholar.google.com/scholar?q=Explicit+v.s.+Implicit+Memory%3A+Exploring+Multi-hop+Complex+Reasoning+Over+Personalized+Information16. Handling Preference Drift in Capturing Dynamic User Preferences for Streaming Session-Based Recommendations — Oussama Alahoum, Boudjemaa Boudaa, Laouni Djafri, 2025/2026https://scholar.google.com/scholar?q=Handling+Preference+Drift+in+Capturing+Dynamic+User+Preferences+for+Streaming+Session-Based+Recommendations17. Episodic Memory in AI Agents Poses Risks That Should Be Studied and Mitigated — Chad DeChant, 2025https://scholar.google.com/scholar?q=Episodic+Memory+in+AI+Agents+Poses+Risks+That+Should+Be+Studied+and+Mitigated18. AI Post Transformers: Memory Sparse Attention for 100M-Token Scaling — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-07-memory-sparse-attention-for-100m-token-s-377cff.mp319. AI Post Transformers: Recursive Language Models for Arbitrarily Long Prompts — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-recursive-language-models-for-arbitraril-fbcd1c.mp320. AI Post Transformers: Neural Computers as Learned Latent Runtimes — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-11-neural-computers-as-learned-latent-runti-9fa282.mp321. AI Post Transformers: How Induction Heads Emerge in Transformers — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-05-03-how-induction-heads-emerge-in-transforme-a7bfcb.mp3Interactive Visualization: EverMemOS for Long-Horizon Agent Memory0 min
- When LLM Judges Become Coin FlipsThis episode explores a March 2026 paper arguing that LLM-based judges are an unreliable way to measure jailbreak success and adversarial robustness. It explains how modern safety evaluations rely on judge models to score harmful outputs, then walks through why those judges can break under attack shift, model shift, and data shift, sometimes degrading to near coin-flip reliability. The discussion connects this critique to benchmarks such as MT-Bench, HarmBench, and StrongREJECT, and examines how weaknesses in the judging pipeline can inflate or distort reported attack success rates. Listeners would find it interesting because it challenges whether many headline jailbreak results are exposing real model failures or simply failures in the grading system.Sources:1. A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness — Leo Schwinn, Moritz Ladenburger, Tim Beyer, Mehrnaz Mofakhami, Gauthier Gidel, Stephan Günnemann, 2026http://arxiv.org/abs/2603.065942. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena — Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zi Lin, Zhuohan Li, Joseph E. Gonzalez, Ion Stoica and others, 2023https://scholar.google.com/scholar?q=Judging+LLM-as-a-Judge+with+MT-Bench+and+Chatbot+Arena3. Large Language Models are not Fair Evaluators — Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Qi Liu, Tianyu Liu, Zhifang Sui, 2023https://scholar.google.com/scholar?q=Large+Language+Models+are+not+Fair+Evaluators4. An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Models are Task-specific Classifiers — Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Tiejun Zhao, 2024https://scholar.google.com/scholar?q=An+Empirical+Study+of+LLM-as-a-Judge+for+LLM+Evaluation%3A+Fine-tuned+Judge+Models+are+Task-specific+Classifiers5. JudgeBench: A Benchmark for Evaluating LLM-based Judges — Sijun Tan, Siyuan Zhuang, Kyle Montgomery, William Y. Tang, Alejandro Cuadron, Chenguang Wang, Raluca Ada Popa, Ion Stoica, 2024https://scholar.google.com/scholar?q=JudgeBench%3A+A+Benchmark+for+Evaluating+LLM-based+Judges6. Universal and Transferable Adversarial Attacks on Aligned Language Models — Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, Matt Fredrikson, 2023https://scholar.google.com/scholar?q=Universal+and+Transferable+Adversarial+Attacks+on+Aligned+Language+Models7. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal — Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, David Forsyth, Dan Hendrycks, 2024https://scholar.google.com/scholar?q=HarmBench%3A+A+Standardized+Evaluation+Framework+for+Automated+Red+Teaming+and+Robust+Refusal8. A StrongREJECT for Empty Jailbreaks — Alexandra Souly, Qingyuan Lu, Dillon Bowen, Tu Trinh, Elvis Hsieh, Sana Pandey, Pieter Abbeel, Justin Svegliato, Scott Emmons, Olivia Watkins, Sam Toyer, 2024https://scholar.google.com/scholar?q=A+StrongREJECT+for+Empty+Jailbreaks9. JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models — Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong, 2024https://scholar.google.com/scholar?q=JailbreakBench%3A+An+Open+Robustness+Benchmark+for+Jailbreaking+Large+Language+Models10. Dataset Shift in Machine Learning — Joaquin Quiñonero-Candela, Masashi Sugiyama, Anton Schwaighofer, Neil D. Lawrence (editors), 2008https://scholar.google.com/scholar?q=Dataset+Shift+in+Machine+Learning11. Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift — Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, D. Sculley, Sebastian Nowozin, Joshua Dillon, Balaji Lakshminarayanan, Jasper Snoek, 2019https://scholar.google.com/scholar?q=Can+You+Trust+Your+Model%27s+Uncertainty%3F+Evaluating+Predictive+Uncertainty+Under+Dataset+Shift12. Measuring Robustness to Natural Distribution Shifts in Image Classification — Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, Ludwig Schmidt, 2020https://scholar.google.com/scholar?q=Measuring+Robustness+to+Natural+Distribution+Shifts+in+Image+Classification13. WILDS: A Benchmark of in-the-Wild Distribution Shifts — Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Percy Liang and others, 2021https://scholar.google.com/scholar?q=WILDS%3A+A+Benchmark+of+in-the-Wild+Distribution+Shifts14. LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge — Shuaizhi Li, Chenxu Xu, Jiazhu Wang, Xianyu Gong, Cheng Chen, Jun Zhang, Junjie Wang, Kit Lam, and Shouling Ji, 2025https://scholar.google.com/scholar?q=LLMs+Cannot+Reliably+Judge+%28Yet%3F%29%3A+A+Comprehensive+Assessment+on+the+Robustness+of+LLM-as-a-Judge15. Confusion Is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs — Yixin Yan, Shichao Sun, Zhen Wang, Yifan Lin, Zeyu Duan, Zhenzhen Zheng, Mingyu Liu, Zhenfei Yin, and Jie Zhang, 2025https://scholar.google.com/scholar?q=Confusion+Is+the+Final+Barrier%3A+Rethinking+Jailbreak+Evaluation+and+Investigating+the+Real+Misuse+Threat+of+LLMs16. Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges — Francisco Eiras et al., 2025https://scholar.google.com/scholar?q=Know+Thy+Judge%3A+On+the+Robustness+Meta-Evaluation+of+LLM+Safety+Judges17. Comparison Requires Valid Measurement: Rethinking Attack Success Rate Comparisons in AI Red Teaming — Alexandra Chouldechova, A. Feder Cooper, Solon Barocas, Abhinav Palia, Dan Vann, Hanna Wallach, 2025/2026https://scholar.google.com/scholar?q=Comparison+Requires+Valid+Measurement%3A+Rethinking+Attack+Success+Rate+Comparisons+in+AI+Red+Teaming18. How to Correctly Report LLM-as-a-Judge Evaluations — Chungpa Lee et al., 2025https://scholar.google.com/scholar?q=How+to+Correctly+Report+LLM-as-a-Judge+Evaluations19. Embracing Ambiguity: Bayesian Nonparametrics and Stakeholder Participation for Ambiguity-Aware Safety Evaluation — Yanan Long, 2025/2026https://scholar.google.com/scholar?q=Embracing+Ambiguity%3A+Bayesian+Nonparametrics+and+Stakeholder+Participation+for+Ambiguity-Aware+Safety+Evaluation20. AI Post Transformers: Multidimensional Safety Evaluation of Frontier AI Models — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/multidimensional-safety-evaluation-of-frontier-ai-models/21. AI Post Transformers: LLM Benchmark Robustness to Linguistic Variation — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/llm-benchmark-robustness-to-linguistic-variation/22. AI Post Transformers: AI Agent Traps and Prompt Injection — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-02-ai-agent-traps-and-prompt-injection-7ce4ba.mp3Interactive Visualization: When LLM Judges Become Coin Flips15 min
- Generative Modeling via Drifting in One StepThis episode explores a 2026 paper, Generative Modeling via Drifting, which argues that the hard transport process behind modern generative models can be moved into training so that inference becomes a single forward pass. It explains the core idea of a pushforward distribution, introduces the paper’s notion of a drifting field that nudges generated samples toward the data distribution during optimization, and frames equilibrium as the point where those updates no longer need to move samples. The discussion compares this approach with GANs, diffusion models, flow matching, and other fast one-step systems, highlighting the tradeoff between low-latency generation and the quality advantages of multi-step correction. A listener would find it interesting because it lays out a possible new generative modeling paradigm and tests whether one-shot generation can become more than just an accelerated approximation of diffusion.Sources:1. Generative Modeling via Drifting — Mingyang Deng, He Li, Tianhong Li, Yilun Du, Kaiming He, 2026http://arxiv.org/abs/2602.047702. Generative Adversarial Nets — Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2014https://neurips.cc/virtual/2014/poster/46183. Generative Moment Matching Networks — Yujia Li, Kevin Swersky, Rich Zemel, 2015https://proceedings.mlr.press/v37/li15.html4. Consistency Models — Yang Song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever, 2023https://icml.cc/virtual/2023/poster/245935. Adversarial Diffusion Distillation — Stability AI researchers, 2023https://stability.ai/research/adversarial-diffusion-distillation6. A Kernel Two-Sample Test — Arthur Gretton, Karsten M. Borgwardt, Malte J. Rasch, Bernhard Scholkopf, Alexander Smola, 2012https://www.jmlr.org/beta/papers/v13/gretton12a.html7. Wasserstein GAN — Martin Arjovsky, Soumith Chintala, Leon Bottou, 2017https://icml.cc/virtual/2017/poster/7998. Density Estimation using Real NVP — Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio, 2017https://openreview.net/forum?id=HkpbnH9lx9. Glow: Generative Flow with Invertible 1x1 Convolutions — Diederik P. Kingma, Prafulla Dhariwal, 2018https://openai.com/index/glow/10. Flow Matching for Generative Modeling — Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, Matt Le, 2023https://openreview.net/forum?id=PqvMRDCJT9t11. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow — Xingchao Liu, Chengyue Gong, Qiang Liu, 2022https://openreview.net/forum?id=gWxpdtQpiYV12. Large Scale GAN Training for High Fidelity Natural Image Synthesis — Andrew Brock, Jeff Donahue, Karen Simonyan, 2018https://huggingface.co/papers/1809.1109613. Diffusion Models Beat GANs on Image Synthesis — Prafulla Dhariwal, Alex Nichol, 2021https://openreview.net/forum?id=AAWuCvzaVt14. High-Resolution Image Synthesis with Latent Diffusion Models — Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Bjorn Ommer, 2022https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html15. Scalable Diffusion Models with Transformers — William Peebles, Saining Xie, 2023https://openaccess.thecvf.com/content/ICCV2023/html/Peebles_Scalable_Diffusion_Models_with_Transformers_ICCV_2023_paper.html16. Denoising Diffusion Probabilistic Models — Jonathan Ho, Ajay Jain, Pieter Abbeel, 2020https://scholar.google.com/scholar?q=Denoising+Diffusion+Probabilistic+Models17. Progressive Distillation for Fast Sampling of Diffusion Models — Tim Salimans, Jonathan Ho, 2022https://scholar.google.com/scholar?q=Progressive+Distillation+for+Fast+Sampling+of+Diffusion+Models18. Unsupervised Image-to-Image Translation Networks — Ferenc Huszar and coauthors are not cited here; instead the more relevant cited moment-matching line is:, 2015https://scholar.google.com/scholar?q=Unsupervised+Image-to-Image+Translation+Networks19. Auto-Encoding Variational Bayes — Diederik P. Kingma, Max Welling, 2013https://scholar.google.com/scholar?q=Auto-Encoding+Variational+Bayes20. One-step diffusion with distribution matching distillation — approx. diffusion-distillation literature, recenthttps://scholar.google.com/scholar?q=One-step+diffusion+with+distribution+matching+distillation21. One-step diffusion distillation via deep equilibrium models — approx. diffusion-distillation / equilibrium-model authors, recenthttps://scholar.google.com/scholar?q=One-step+diffusion+distillation+via+deep+equilibrium+models22. Discrete Flow Matching — approx. flow-matching authors, recenthttps://scholar.google.com/scholar?q=Discrete+Flow+Matching23. Elucidating the design choice of probability paths in flow matching for forecasting — approx. forecasting / flow-matching authors, recenthttps://scholar.google.com/scholar?q=Elucidating+the+design+choice+of+probability+paths+in+flow+matching+for+forecasting24. Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation — approx. hybrid AR-diffusion authors, recenthttps://scholar.google.com/scholar?q=Mixed+Autoregressive+and+Diffusion+Transformers+for+Continuous+Image+Generation25. ACDiT: Interpolating autoregressive conditional modeling and diffusion transformer — approx. ACDiT authors, 2025https://scholar.google.com/scholar?q=ACDiT%3A+Interpolating+autoregressive+conditional+modeling+and+diffusion+transformer26. AI Post Transformers: Paris: Decentralized Open-Weight Diffusion Model — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/paris-decentralized-open-weight-diffusion-model/Interactive Visualization: Generative Modeling via Drifting in One Step14 min
- LAPS for Length-Aware LLM ServingThis episode explores LAPS, a serving system for large language models that treats long prompt prefills and short multi-turn re-prefills as fundamentally different workloads instead of batching them together. It explains why user-perceived latency, especially time to first token, suffers when tiny follow-up requests get stuck behind large compute-heavy context loads, and how LAPS models the boundary between compute-bound and memory-bound prefills to separate them more intelligently. The discussion covers LAPS’s dual-queue design, its temporal and spatial disaggregation strategies, and engineering choices like short-request waiting windows, length-aware smart batching, and CUDA Graph execution. Listeners would find it interesting because it connects low-level scheduling and KV-cache behavior to the everyday experience of whether chat systems feel fast and responsive.Sources:1. LAPS: A Length-Aware-Prefill LLM Serving System — Jianshu She, Zonghang Li, Hongchao Du, Shangyu Wu, Wenhao Zheng, Eric Xing, Zhengzhong Liu, Huaxiu Yao, Jason Xue, Qirong Ho, 2026http://arxiv.org/abs/2601.115892. ORCA: A Distributed Serving System for Transformer-Based Generative Models — Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, Byung-Gon Chun, 2022https://scholar.google.com/scholar?q=ORCA%3A+A+Distributed+Serving+System+for+Transformer-Based+Generative+Models3. Efficient Memory Management for Large Language Model Serving with PagedAttention — Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, Ion Stoica, 2023https://scholar.google.com/scholar?q=Efficient+Memory+Management+for+Large+Language+Model+Serving+with+PagedAttention4. SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills — Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, 2023https://scholar.google.com/scholar?q=SARATHI%3A+Efficient+LLM+Inference+by+Piggybacking+Decodes+with+Chunked+Prefills5. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving — Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, Hao Zhang, 2024https://scholar.google.com/scholar?q=DistServe%3A+Disaggregating+Prefill+and+Decoding+for+Goodput-optimized+Large+Language+Model+Serving6. BucketServe: Bucket-Based Dynamic Batching for Smart and Efficient LLM Inference Serving — Wanyi Zheng, Minxian Xu, Shengye Song, Kejiang Ye, 2025https://scholar.google.com/scholar?q=BucketServe%3A+Bucket-Based+Dynamic+Batching+for+Smart+and+Efficient+LLM+Inference+Serving7. DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving — Foteini Strati, Sara McAllister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic, 2024https://scholar.google.com/scholar?q=D%C3%A9j%C3%A0Vu%3A+KV-cache+Streaming+for+Fast%2C+Fault-tolerant+Generative+LLM+Serving8. Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving — approx. contemporary LLM systems authors, 2025https://scholar.google.com/scholar?q=Prefill-Decode+Aggregation+or+Disaggregation%3F+Unifying+Both+for+Goodput-Optimized+LLM+Serving9. FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving — approx. contemporary LLM serving authors, 2025https://scholar.google.com/scholar?q=FlowPrefill%3A+Decoupling+Preemption+from+Prefill+Scheduling+Granularity+to+Mitigate+Head-of-Line+Blocking+in+LLM+Serving10. BurstGPT: A Real-World Workload Dataset to Optimize LLM Serving Systems — approx. systems/data-center workload authors, 2025https://scholar.google.com/scholar?q=BurstGPT%3A+A+Real-World+Workload+Dataset+to+Optimize+LLM+Serving+Systems11. SageServe: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-Scaling — approx. cloud systems authors, 2025https://scholar.google.com/scholar?q=SageServe%3A+Optimizing+LLM+Serving+on+Cloud+Data+Centers+with+Forecast+Aware+Auto-Scaling12. ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production — approx. production-serving measurement authors, 2025https://scholar.google.com/scholar?q=ServeGen%3A+Workload+Characterization+and+Generation+of+Large+Language+Model+Serving+in+Production13. Fairness in Serving Large Language Models — approx. theory/systems fairness authors, 2025https://scholar.google.com/scholar?q=Fairness+in+Serving+Large+Language+Models14. FairBatching: Fairness-Aware Batch Formation for LLM Inference — approx. LLM inference scheduling authors, 2025https://scholar.google.com/scholar?q=FairBatching%3A+Fairness-Aware+Batch+Formation+for+LLM+Inference15. Locality-Aware Fair Scheduling in LLM Serving — approx. LLM serving systems authors, 2025https://scholar.google.com/scholar?q=Locality-Aware+Fair+Scheduling+in+LLM+Serving16. AI Post Transformers: Splitwise: Phase-Split LLM Inference — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-26-splitwise-phase-split-llm-inference-e8945b.mp317. AI Post Transformers: Prefill-as-a-Service for Cross-Datacenter KV Cache — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-19-prefill-as-a-service-for-cross-datacente-7560be.mp318. AI Post Transformers: Speculative Decoding in Real vLLM Serving — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-speculative-decoding-in-real-vllm-servin-6f4e2b.mp319. AI Post Transformers: Breaking the Prefix Barrier with Shared KV Cache — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-24-breaking-the-prefix-barrier-with-shared-a5e5a6.mp320. AI Post Transformers: Computation-Bandwidth-Memory Trade-offs for AI Infrastructure — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-09-computation-bandwidth-memory-trade-offs-a83f2b.mp3Interactive Visualization: LAPS for Length-Aware LLM Serving13 min
- Backpropagation Through Time ExplainedThis episode explores Paul Werbos’s 1990 paper on Backpropagation Through Time and explains how ordinary backpropagation extends to systems whose state evolves over time. It walks through the core idea of unrolling a recurrent or dynamic system into a time-indexed computation graph, then applying reverse-mode differentiation to compute exact gradients across both layers and time steps. The discussion also places BPTT in historical context, connecting it to earlier work on backpropagation, automatic differentiation, and alternative recurrent learning methods like real-time recurrent learning. Listeners would find it interesting because it shows how a foundational training method for sequence models, control systems, and differentiable simulations emerged from a simple but powerful reframing of memory and time in neural computation.Sources:1. Backpropagation Through Time Explainedhttps://podcast.do-not-panic.com/uploaded-pdfs/2026-05-08T22-17-15-230Z-Backpropagation-through-time-what-it-does-and-how-to-do-it.pdf2. Learning representations by back-propagating errors — David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams, 1986https://scholar.google.com/scholar?q=Learning+representations+by+back-propagating+errors3. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks — Ronald J. Williams, David Zipser, 1989https://scholar.google.com/scholar?q=A+Learning+Algorithm+for+Continually+Running+Fully+Recurrent+Neural+Networks4. Backpropagation Through Time: What It Does and How to Do It — Paul J. Werbos, 1990https://scholar.google.com/scholar?q=Backpropagation+Through+Time%3A+What+It+Does+and+How+to+Do+It5. Learning long-term dependencies with gradient descent is difficult — Yoshua Bengio, Patrice Simard, Paolo Frasconi, 1994https://scholar.google.com/scholar?q=Learning+long-term+dependencies+with+gradient+descent+is+difficult6. Long Short-Term Memory — Sepp Hochreiter, Jürgen Schmidhuber, 1997https://scholar.google.com/scholar?q=Long+Short-Term+Memory7. Taylor expansion of the accumulated rounding error — Seppo Linnainmaa, 1976https://scholar.google.com/scholar?q=Taylor+expansion+of+the+accumulated+rounding+error8. Fast Exact Multiplication by the Hessian — Barak A. Pearlmutter, 1994https://scholar.google.com/scholar?q=Fast+Exact+Multiplication+by+the+Hessian9. Automatic Differentiation in Machine Learning: a Survey — Atilim Gunes Baydin, Barak A. Pearlmutter, Alexey Andreyevich Radul, Jeffrey Mark Siskind, 2018https://scholar.google.com/scholar?q=Automatic+Differentiation+in+Machine+Learning%3A+a+Survey10. A review of automatic differentiation and its efficient implementation — Charles C. Margossian, 2019https://scholar.google.com/scholar?q=A+review+of+automatic+differentiation+and+its+efficient+implementation11. Generalization of Back-Propagation to Recurrent Neural Networks — Fernando J. Pineda, 1987https://scholar.google.com/scholar?q=Generalization+of+Back-Propagation+to+Recurrent+Neural+Networks12. Finding Structure in Time — Jeffrey L. Elman, 1990https://scholar.google.com/scholar?q=Finding+Structure+in+Time13. BP(lambda): Online Learning via Synthetic Gradients — approx. anonymous from snippet / modern deep learning authors, recenthttps://scholar.google.com/scholar?q=BP%28lambda%29%3A+Online+Learning+via+Synthetic+Gradients14. Streaming Propagation Through Time: A New Computational Paradigm for Recurrent Neural Networks — approx. modern recurrent-learning authors, recenthttps://scholar.google.com/scholar?q=Streaming+Propagation+Through+Time%3A+A+New+Computational+Paradigm+for+Recurrent+Neural+Networks15. Combining Truncated BPTT and Truncated RTRL for LSTM Training — Jakob Stefan Weber, recenthttps://scholar.google.com/scholar?q=Combining+Truncated+BPTT+and+Truncated+RTRL+for+LSTM+Training16. Second-order forward-mode optimization of recurrent neural networks for neuroscience — approx. modern neuroscience/optimization authors, recenthttps://scholar.google.com/scholar?q=Second-order+forward-mode+optimization+of+recurrent+neural+networks+for+neuroscience17. Sample-Based Hybrid Mode Control: Asymptotically Optimal Switching of Algorithmic and Non-Differentiable Control Modes — approx. modern control authors, recenthttps://scholar.google.com/scholar?q=Sample-Based+Hybrid+Mode+Control%3A+Asymptotically+Optimal+Switching+of+Algorithmic+and+Non-Differentiable+Control+Modes18. On the differentiability of the value function of switched linear systems under arbitrary and controlled switching — approx. control theory authors, recenthttps://scholar.google.com/scholar?q=On+the+differentiability+of+the+value+function+of+switched+linear+systems+under+arbitrary+and+controlled+switching19. AI Post Transformers: Long Short-Term Memory and Vanishing Gradients — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-19-long-short-term-memory-and-vanishing-gra-72448c.mp320. AI Post Transformers: When Spectral Gradient Updates Help Deep Learning — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-when-spectral-gradient-updates-help-deep-9c8441.mp3Interactive Visualization: Backpropagation Through Time Explained14 min
- Learning in Random Nets and GeneralizationThis episode explores Marvin Minsky’s 1961 paper on whether mostly random neural networks can learn useful behavior simply by reinforcing successful responses. It explains how the paper distinguishes rote memory, associative recall, pattern recognition, and true generalization, arguing that reward signals alone are not enough unless the system already has a meaningful notion of similarity between situations. The discussion places that idea in context with early machine learning work like Rosenblatt’s perceptron and Samuel’s checkers program, then connects it to later, more disciplined descendants such as echo state networks and random features. Listeners get a sharp historical view of a debate that still matters now: whether intelligence comes from discovering good representations or from selecting among structures that were already there.Sources:1. Learning in Random Nets and Generalizationhttps://stacks.stanford.edu/file/druid:yr384hg3073/yr384hg3073.pdf2. Learning in Random Nets — Marvin Minsky, Oliver G. Selfridge, 1961https://scholar.google.com/scholar?q=Learning+in+Random+Nets3. The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain — Frank Rosenblatt, 1958https://scholar.google.com/scholar?q=The+Perceptron%3A+A+Probabilistic+Model+for+Information+Storage+and+Organization+in+the+Brain4. The Echo State Approach to Analysing and Training Recurrent Neural Networks — Herbert Jaeger, 2001https://scholar.google.com/scholar?q=The+Echo+State+Approach+to+Analysing+and+Training+Recurrent+Neural+Networks5. Random Features for Large-Scale Kernel Machines — Ali Rahimi, Benjamin Recht, 2007https://scholar.google.com/scholar?q=Random+Features+for+Large-Scale+Kernel+Machines6. The Use of Multiple Measurements in Taxonomic Problems — R. A. Fisher, 1936https://scholar.google.com/scholar?q=The+Use+of+Multiple+Measurements+in+Taxonomic+Problems7. Nearest Neighbor Pattern Classification — Thomas M. Cover, Peter E. Hart, 1967https://scholar.google.com/scholar?q=Nearest+Neighbor+Pattern+Classification8. Support-Vector Networks — Corinna Cortes, Vladimir Vapnik, 1995https://scholar.google.com/scholar?q=Support-Vector+Networks9. Gradient-Based Learning Applied to Document Recognition — Yann LeCun, Leon Bottou, Yoshua Bengio, Patrick Haffner, 1998https://scholar.google.com/scholar?q=Gradient-Based+Learning+Applied+to+Document+Recognition10. Some Studies in Machine Learning Using the Game of Checkers — Arthur L. Samuel, 1959https://scholar.google.com/scholar?q=Some+Studies+in+Machine+Learning+Using+the+Game+of+Checkers11. Generalization of Pattern Recognition in a Self-Organizing System — B. G. Farley and W. A. Clark, 1954https://scholar.google.com/scholar?q=Generalization+of+Pattern+Recognition+in+a+Self-Organizing+System12. A Heterarchy of Values Determined by the Topology of Nervous Nets — Warren S. McCulloch, 1945https://scholar.google.com/scholar?q=A+Heterarchy+of+Values+Determined+by+the+Topology+of+Nervous+Nets13. Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime — Hong Hu, Yue M. Lu, Theodor Misiakiewicz, 2024https://scholar.google.com/scholar?q=Asymptotics+of+Random+Feature+Regression+Beyond+the+Linear+Scaling+Regime14. Power-Law Spectrum of the Random Feature Model — Elliot Paquette, Ke Liang Xiao, Yizhe Zhu, 2026https://scholar.google.com/scholar?q=Power-Law+Spectrum+of+the+Random+Feature+Model15. Local to Global: Learning Dynamics and Effect of Initialization for Transformers — Ashok Vardhan Makkuva, Marco Bondaschi, Chanakya Ekbote, Adway Girish, Alliot Nagle, Hyeji Kim, Michael Gastpar, 2024https://scholar.google.com/scholar?q=Local+to+Global%3A+Learning+Dynamics+and+Effect+of+Initialization+for+Transformers16. Augmenting Language Models with Long-Term Memory — Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, Furu Wei, 2023https://scholar.google.com/scholar?q=Augmenting+Language+Models+with+Long-Term+Memory17. MemoryBank: Enhancing Large Language Models with Long-Term Memory — Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, Yanlin Wang, 2023https://scholar.google.com/scholar?q=MemoryBank%3A+Enhancing+Large+Language+Models+with+Long-Term+Memory18. HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models — Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su, 2024https://scholar.google.com/scholar?q=HippoRAG%3A+Neurobiologically+Inspired+Long-Term+Memory+for+Large+Language+Models19. The Learnability of In-Context Learning — Noam Wies, Yoav Levine, Amnon Shashua, 2023https://scholar.google.com/scholar?q=The+Learnability+of+In-Context+Learning20. Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions — Satwik Bhattamishra, Arkil Patel, Phil Blunsom, Varun Kanade, 2023https://scholar.google.com/scholar?q=Understanding+In-Context+Learning+in+Transformers+and+LLMs+by+Learning+to+Learn+Discrete+Functions21. Learning without Training: The Implicit Dynamics of In-Context Learning — Benoit Dherin, Michael Munn, Hanna Mazzawi, Michael Wunder, Javier Gonzalvo, 2025https://scholar.google.com/scholar?q=Learning+without+Training%3A+The+Implicit+Dynamics+of+In-Context+Learning22. AI Post Transformers: Long Short-Term Memory and Vanishing Gradients — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-19-long-short-term-memory-and-vanishing-gra-72448c.mp323. AI Post Transformers: Latent Space as a New Computational Paradigm — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-05-latent-space-as-a-new-computational-para-810f39.mp324. AI Post Transformers: When Spectral Gradient Updates Help Deep Learning — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-when-spectral-gradient-updates-help-deep-9c8441.mp325. AI Post Transformers: LeWorldModel: Stable Joint-Embedding World Models from Pixels — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-25-leworldmodel-stable-joint-embedding-worl-650f9f.mp3Interactive Visualization: Learning in Random Nets and Generalization15 min
- What the Frog’s Eye Tells the BrainThis episode explores the 1959 paper on frog vision that argued the retina does far more than passively relay a camera-like image to the brain. It explains how experiments on single optic nerve fibers revealed specialized visual detectors tuned to ecologically relevant signals such as small moving dark objects, edges, dimming, and contrast changes, rather than raw brightness alone. The discussion connects these findings to modern machine learning ideas like preprocessing, receptive fields, sparse event-driven signals, and early feature extraction, while also emphasizing where biological retinal circuits differ sharply from engineered neural networks. A listener would find it interesting because it shows how a foundational neuroscience experiment anticipated core ideas in AI and neural coding by asking what information an animal actually needs to survive.Sources:1. What the Frog’s Eye Tells the Brainhttps://courses.csail.mit.edu/6.803/pdf/lettvin.pdf2. The Response of Single Optic Nerve Fibers of the Vertebrate Eye to Illumination of the Retina — H. Keffer Hartline, 1938https://scholar.google.com/scholar?q=The+Response+of+Single+Optic+Nerve+Fibers+of+the+Vertebrate+Eye+to+Illumination+of+the+Retina3. Discharge Patterns and Functional Organization of Mammalian Retina — Stephen W. Kuffler, 1953https://scholar.google.com/scholar?q=Discharge+Patterns+and+Functional+Organization+of+Mammalian+Retina4. Anatomy and Physiology of Vision in the Frog (Rana pipiens) — Humberto R. Maturana, Jerome Y. Lettvin, Warren S. McCulloch, Walter H. Pitts, 1960https://scholar.google.com/scholar?q=Anatomy+and+Physiology+of+Vision+in+the+Frog+%28Rana+pipiens%295. The Dynamic Receptive Fields of Retinal Ganglion Cells — Sophia Wienbar, Gregory W. Schwartz, 2018https://scholar.google.com/scholar?q=The+Dynamic+Receptive+Fields+of+Retinal+Ganglion+Cells6. What the Frog's Eye Tells the Frog's Brain — Jerome Y. Lettvin, Humberto R. Maturana, Warren S. McCulloch, Walter H. Pitts, 1959https://scholar.google.com/scholar?q=What+the+Frog%27s+Eye+Tells+the+Frog%27s+Brain7. Summation and Inhibition in the Frog's Retina — Horace B. Barlow, 1953https://scholar.google.com/scholar?q=Summation+and+Inhibition+in+the+Frog%27s+Retina8. The Mechanism of Directionally Selective Units in Rabbit's Retina — Horace B. Barlow, William R. Levick, 1965https://scholar.google.com/scholar?q=The+Mechanism+of+Directionally+Selective+Units+in+Rabbit%27s+Retina9. The Retina Dissects the Visual Scene into Distinct Features — Botond Roska, Markus Meister, 2014https://scholar.google.com/scholar?q=The+Retina+Dissects+the+Visual+Scene+into+Distinct+Features10. Possible Principles Underlying the Transformations of Sensory Messages — Horace B. Barlow, 1961https://scholar.google.com/scholar?q=Possible+Principles+Underlying+the+Transformations+of+Sensory+Messages11. The Neural Code of the Retina — Markus Meister, Michael J. Berry II, 1999https://scholar.google.com/scholar?q=The+Neural+Code+of+the+Retina12. Weak Pairwise Correlations Imply Strongly Correlated Network States in a Neural Population — Elad Schneidman, Michael J. Berry II, Ronen Segev, William Bialek, 2006https://scholar.google.com/scholar?q=Weak+Pairwise+Correlations+Imply+Strongly+Correlated+Network+States+in+a+Neural+Population13. Spatio-temporal Correlations and Visual Signalling in a Complete Neuronal Population — Jonathan W. Pillow, Jonathon Shlens, Liam Paninski, Alexander Sher, Alan M. Litke, E. J. Chichilnisky, Eero P. Simoncelli, 2008https://scholar.google.com/scholar?q=Spatio-temporal+Correlations+and+Visual+Signalling+in+a+Complete+Neuronal+Population14. Receptive Fields of Single Neurones in the Cat's Striate Cortex — D. H. Hubel and T. N. Wiesel, 1959https://scholar.google.com/scholar?q=Receptive+Fields+of+Single+Neurones+in+the+Cat%27s+Striate+Cortex15. Interpreting the retinal neural code for natural scenes: From computations to neurons — Maheswaranathan, McIntosh, Tanaka, Baccus et al., 2023https://scholar.google.com/scholar?q=Interpreting+the+retinal+neural+code+for+natural+scenes%3A+From+computations+to+neurons16. Spatial adaptation of primate retinal ganglion cells between artificial and natural stimuli — Vystrcilova, Sridhar, Burg, Gollisch, Ecker et al., 2025/2026https://scholar.google.com/scholar?q=Spatial+adaptation+of+primate+retinal+ganglion+cells+between+artificial+and+natural+stimuli17. Distributed feature representations of natural stimuli across parallel retinal pathways — Hsiang, Shen, Soto, Kerschensteiner et al., 2024https://scholar.google.com/scholar?q=Distributed+feature+representations+of+natural+stimuli+across+parallel+retinal+pathways18. Retinal motion statistics during natural locomotion — Muller, Matthis, Bonnen, Cormack, Huk, Hayhoe, 2023https://scholar.google.com/scholar?q=Retinal+motion+statistics+during+natural+locomotion19. Natural visual behavior and active sensing in the mouse — review by members of the Niell lab and colleagues, 2024https://scholar.google.com/scholar?q=Natural+visual+behavior+and+active+sensing+in+the+mouse20. A genetically defined tecto-thalamic pathway drives a system of superior-colliculus-dependent visual cortices — Brenner, Beltramo, Gerfen, Ruediger, Scanziani, 2023https://scholar.google.com/scholar?q=A+genetically+defined+tecto-thalamic+pathway+drives+a+system+of+superior-colliculus-dependent+visual+corticesInteractive Visualization: What the Frog’s Eye Tells the Brain10 min
- How Models Detect Hidden Activation SteeringThis episode explores a mechanistic interpretability study asking whether a language model can detect when a concept has been injected into its hidden activations and, in some cases, identify what that concept was. It explains the difference between detection and identification, walks through activation steering in the residual stream, and highlights the paper’s controlled experiments on Gemma3-27B across 500 concepts, including a strong result of moderate detection with zero false positives under several prompt styles. The discussion also focuses on the paper’s argument that this reporting behavior emerges mainly during post-training, especially preference optimization, rather than from pretraining alone. Listeners would find it interesting because it turns a provocative claim about model “introspection” into a concrete circuit-level question about what internal features and gates may be doing.Sources:1. Mechanisms of Introspective Awareness — Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey, 2026http://arxiv.org/abs/2603.213962. Emergent Introspective Awareness in Large Language Models — Jack Lindsey, 2025https://scholar.google.com/scholar?q=Emergent+Introspective+Awareness+in+Large+Language+Models3. Looking Inward: Language Models Can Learn About Themselves by Introspection — Felix J. Binder, James Chua, Tomek Korbak, Henry Sleight, John Hughes, Robert Long, Ethan Perez, Miles Turpin, Owain Evans, 2024https://scholar.google.com/scholar?q=Looking+Inward%3A+Language+Models+Can+Learn+About+Themselves+by+Introspection4. Activation Addition: Steering Language Models Without Optimization — Alexander Matt Turner, Lisa Thiergart, David Udell, Gavin Leech, Ulisse Mini, Monte MacDiarmid, Chris Olah, 2023https://scholar.google.com/scholar?q=Activation+Addition%3A+Steering+Language+Models+Without+Optimization5. Representation Engineering: A Top-Down Approach to AI Transparency — Andy Zou, Long Phan, Sarah Chen, James Campbell, Richard Ngo, Adam Jermyn, Stephen McAleer, Alexander Tamkin, 2023https://scholar.google.com/scholar?q=Representation+Engineering%3A+A+Top-Down+Approach+to+AI+Transparency6. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet — Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, and others, 2024https://scholar.google.com/scholar?q=Scaling+Monosemanticity%3A+Extracting+Interpretable+Features+from+Claude+3+Sonnet7. Circuit Tracing: Revealing Computational Graphs in Language Models — Emmanuel Ameisen, Jack Lindsey, Adam Pearce, Wes Gurnee, Nicholas L. Turner, Brian Chen, Craig Citro, and others, 2025https://scholar.google.com/scholar?q=Circuit+Tracing%3A+Revealing+Computational+Graphs+in+Language+Models8. Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=Steering+Vector+Fields+for+Context-Aware+Inference-Time+Control+in+Large+Language+Models9. No Training Wheels: Steering Vectors for Bias Correction at Inference Time — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=No+Training+Wheels%3A+Steering+Vectors+for+Bias+Correction+at+Inference+Time10. A mechanistic understanding of alignment algorithms: A case study on DPO and toxicity — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=A+mechanistic+understanding+of+alignment+algorithms%3A+A+case+study+on+DPO+and+toxicity11. How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=How+Does+DPO+Reduce+Toxicity%3F+A+Mechanistic+Neuron-Level+Analysis12. Refusal in language models is mediated by a single direction — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=Refusal+in+language+models+is+mediated+by+a+single+direction13. Beyond I'm Sorry, I Can't: Dissecting Large-Language-Model Refusal — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=Beyond+I%27m+Sorry%2C+I+Can%27t%3A+Dissecting+Large-Language-Model+Refusal14. Surgical, cheap, and flexible: Mitigating false refusal in language models via single vector ablation — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=Surgical%2C+cheap%2C+and+flexible%3A+Mitigating+false+refusal+in+language+models+via+single+vector+ablation15. Residual stream analysis with multi-layer saes — authors unclear from snippet, 2025/2026https://scholar.google.com/scholar?q=Residual+stream+analysis+with+multi-layer+saes16. AI Post Transformers: Anthropic: Introspective Awareness in LLMs — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/anthropic-introspective-awareness-in-llms/17. AI Post Transformers: Neural Chameleons and Evading Activation Monitors — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-14-neural-chameleons-and-evading-activation-bc470e.mp318. 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/19. AI Post Transformers: How Induction Heads Emerge in Transformers — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-05-03-how-induction-heads-emerge-in-transforme-a7bfcb.mp320. AI Post Transformers: Self-Improving Pretraining With Post-Trained Models — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-05-02-self-improving-pretraining-with-post-tra-e37460.mp3Interactive Visualization: How Models Detect Hidden Activation Steering15 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.