Models & Agents

Models & Agents

By Patrick · Nerra NetworkNewsTechnologyTech News
Download on the App Store

Models & Agents episodes

  • Ep 65: Looking back at 6 episodes from 2026-05-25 to 2026-05-31 — the stories that mattered, what we learned, and what to watch next.
    Models & Agents — Weekly Recap
    Looking back at 6 episodes from 2026-05-25 to 2026-05-31 — the stories that mattered, what we learned, and what to watch next.
    This Week's Top Stories
    ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    0:42 Agent & Tool Developments
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    8 min
  • Ep 64: Windows users can now steer Codex agents directly on their machines while stepping away.
    Models & Agents
    Windows users can now steer Codex agents directly on their machines while stepping away.
    What You Need to Know: OpenAI extended computer-use capabilities to Windows for Codex, letting the agent act on local desktops and continue tasks from the mobile app. StepFun released a 198B MoE vision-language model optimized for coding agents, while Hermes Agent added tool search to reduce MCP context bloat. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    0:36 Agent & Tool Developments
    7:39 Practical & Community
    8:39 Agent & Tool Developments
    11:27 Agent & Tool Developments
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    12 min
  • Ep 63: Anthropic's $65B Series H at $965B valuation and $47B run-rate revenue show Claude demand is scaling faster than most labs can match.
    Models & Agents
    Anthropic's $65B Series H at $965B valuation and $47B run-rate revenue show Claude demand is scaling faster than most labs can match.
    What You Need to Know: Liquid AI shipped LFM2.5-8B-A1B with 128K context and 38T pre-training tokens for edge devices. A new monokernel on AMD MI300X hits 3,300 output tokens/s for small models. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    1:06 Agent & Tool Developments
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    9 min
  • Ep 62: CoreWeave’s new platform lets agents improve themselves between training and inference runs without manual retraining cycles.
    Models & Agents
    CoreWeave’s new platform lets agents improve themselves between training and inference runs without manual retraining cycles.
    What You Need to Know: CoreWeave launched a unified agentic platform that closes the training-to-inference gap for continuous autonomous improvement. Perplexity open-sourced a Unigram tokenizer that cuts reranker latency 5x versus Hugging Face. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    0:33 Agent & Tool Developments
    0:49 Practical & Community
    1:06 Agent & Tool Developments
    1:41 Model Updates
    4:19 Agent & Tool Developments
    9:16 Practical & Community
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    11 min
  • Ep 61: Anthropic just published concrete sandboxing patterns that let agents scale capabilities without expanding their blast radius.
    Models & Agents
    Anthropic just published concrete sandboxing patterns that let agents scale capabilities without expanding their blast radius.
    What You Need to Know: Anthropic released a detailed engineering post on how they contain Claude agents through evolving access controls and sandbox limits. EAGLE 3.1 fixes attention drift in speculative decoding for more stable production inference. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    0:33 Agent & Tool Developments
    1:07 Agent & Tool Developments
    1:46 Model Updates
    3:27 Agent & Tool Developments
    5:16 Practical & Community
    7:15 Things to Try
    7:59 Agent & Tool Developments
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    10 min
  • Ep 60: Local builders can now treat markdown skill files as optimizable parameters with automated validation gates instead of manual tweaking.
    Models & Agents
    Local builders can now treat markdown skill files as optimizable parameters with automated validation gates instead of manual tweaking.
    What You Need to Know: A new paper formalizes SkillOpt, using frontier models to propose bounded edits to markdown skills and accepting only those that improve a held-out validation set. Qwen3.5 and Qwen3.6 receive new uncensored and diffusion variants with detailed training notes for consumer hardware. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    2:14 Agent & Tool Developments
    3:10 Practical & Community
    3:40 Agent & Tool Developments
    6:39 Agent & Tool Developments
    8:42 Practical & Community
    9:17 Agent & Tool Developments
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    12 min
  • Ep 59: Datasette's new slash-key jump menu now launches agent conversations directly from your databases.
    Models & Agents
    Datasette's new slash-key jump menu now launches agent conversations directly from your databases.
    What You Need to Know: Simon Willison shipped Datasette 1.0a30 with a keyboard-driven "jump to" menu that plugins can extend, plus a datasette-agent plugin that adds a conversation starter form. NuExtract3, a new 4B vision-language model, arrived on Hugging Face for structured extraction and Markdown conversion from documents. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    0:37 Agent & Tool Developments
    1:26 Top Story
    1:56 Agent & Tool Developments
    2:20 Model Updates
    4:39 Practical & Community
    5:37 Agent & Tool Developments
    7:00 Agent & Tool Developments
    9:00 Agent & Tool Developments
    9:45 On the Horizon
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    11 min
  • Ep 58: Looking back at 6 episodes from 2026-05-18 to 2026-05-24 — the stories that mattered, what we learned, and what to watch next.
    Models & Agents — Weekly Recap
    Looking back at 6 episodes from 2026-05-18 to 2026-05-24 — the stories that mattered, what we learned, and what to watch next.
    This Week's Top Stories
    From Ep 52 (2026-05-18): What You Need to Know:
    What You Need to Know: NVIDIA released a full 4-bit pretraining stack (NVFP4) that was validated on a 12B Mamba-Transformer trained for 10 trillion tokens. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    1:52 Agent & Tool Developments
    4:10 Practical & Community
    4:25 Agent & Tool Developments
    5:12 Practical & Community
    5:42 Agent & Tool Developments
    6:24 Practical & Community
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    8 min
  • Ep 57: OpenAI just added goal mode and screen-aware context to Codex, letting agents work autonomously for hours on real tasks.
    Models & Agents
    OpenAI just added goal mode and screen-aware context to Codex, letting agents work autonomously for hours on real tasks.
    What You Need to Know: OpenAI rolled out Goal mode, Appshots, and advanced annotation in Codex across app, IDE, and CLI. Anthropic reported finding over 10,000 high-severity vulnerabilities through Project Glasswing using Claude models. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    0:38 Agent & Tool Developments
    1:02 Practical & Community
    1:27 Agent & Tool Developments
    2:43 Practical & Community
    5:16 Agent & Tool Developments
    9:02 Practical & Community
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    12 min
  • Ep 56: OpenAI just gave Codex the ability to control locked Macs and run multi-day goals, turning it into a true background agent you can launch from your phone.
    Models & Agents
    OpenAI just gave Codex the ability to control locked Macs and run multi-day goals, turning it into a true background agent you can launch from your phone.
    What You Need to Know: OpenAI shipped several Codex updates today including secure computer use on locked Macs, Goal mode for hours-long autonomous work, and advanced annotation tools. Microsoft released Fara1.5, a family of browser agents that beat OpenAI Operator and Gemini 2.5 on web tasks. ...
    Chapters:
    0:00 Intro
    0:20 Introduction
    0:31 Agent & Tool Developments
    5:36 Practical & Community
    6:06 Agent & Tool Developments
    9:47 Tomorrow Teaser
    9:57 Agent & Tool Developments
    AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production.
    11 min

About Models & Agents

From the publisher's feed

Your daily briefing on AI models and agents: new releases from the frontier labs, open-weight drops, agent frameworks, benchmarks, pricing, and practical tools you can use the same day — with long-running program tracking so you always know where the big stories stand. For developers, builders, and AI practitioners.