Today I'm releasing my entire newsletter archive (350+ posts) and all podcast transcripts (300+ episodes) as AI-friendly Markdown files. Plus an MCP server and GitHub repo. A few months ago I shared my podcast transcripts on a whim, and y'all built the most amazing things—an RPG
CODE
-
Codex Rate Limited by Excessive Subagent Usage
By
–
lol i got rate limited by codex for using too many subagents
-
OpenAI Launches GPT-5.4 mini, Twice as Fast
By
–
GPT-5.4 mini is available today in ChatGPT, Codex, and the API. Optimized for coding, computer use, multimodal understanding, and subagents. And it's 2x faster than GPT-5 mini. https://openai.com/index/introducing-gpt-5-4-mini-and-nano/ [Translated from EN to English]
-
Heartbeat monitoring for orchestrator and subagents resilience
By
–
add a heartbeat to the orchestrator and the subagents so if they stop they keep going when you do this be careful about the way the model ends it's responses with "here's what i'd do next…" sometimes that's helpufl, but if they're not working from a clear plan you can wake up
-
Framework-specific challenges with VRAM, disk, and quantization options
By
–
Thanks for the feedback. The only problem with VRAM, disk, and quant options is that they are framework specific. Disk is maybe the most obvious or feasible one for a given precision (like bf16)
-
LangSmith Sandboxes: Safe Code Execution for Agents
By
–
🚀 Today we're launching LangSmith Sandboxes
— LangChain (@LangChain) 17 mars 2026
Agents get a lot more useful when they can run code: analyze data, call APIs, build entire applications.
Sandboxes give them a safe place to do it with ephemeral, locked-down environments you control.
Now in Private Preview.
Learn… pic.twitter.com/98kqloy7lhToday we're launching LangSmith Sandboxes Agents get a lot more useful when they can run code: analyze data, call APIs, build entire applications. Sandboxes give them a safe place to do it with ephemeral, locked-down environments you control. Now in Private Preview. Learn
-
Anthropic Launches Remote Control Mobile Version Claude Code
By
–
Anthropic just released a mobile version of Claude Code called Remote Control https://
buff.ly/cenHKRl
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Inference VRAM Complexity Depends on Framework Implementation
By
–
I was thinking about inference VRAM as well, but this one is so tricky because it depends on the implementation/framework one is using
-
Autonomous PR Deployment Using Codex Subagents in Production
By
–
prompt get many PRs to prod autonomously using codex subagents: Run a continuous prod-to-green swarm loop. Keep the immediate blocking task local. Use a small stable set of persistent subagent lanes:
1. prod monitor
2. staging shepherd
3. current/newest pathology investigator -
Distinguishing Open-Weight from Open-Source: License and Code Availability
By
–
It'd be hard to tell whether it's open-weight or open-source because they may both use the same license like MIT, Apache V2 etc. (But the definition of open-source is tricky, some only call it open source if training code is available under open source licenses as well)