Devin Stein

@T_Reaves14 looks awesome! Thanks for joining

1/ I watched LangChain’s webinar on LLM wikis and agent memory and wrote up a working paper from my own small agent-fleet experiments: Soft-Cache: A Human-Supervisable Coherence Protocol for Persistent Agent Fleets github.com/treaves-GSD/so…

@jxnlco @OpenAI @AnthropicAI talented chefs

@devstein64 @OpenAI @AnthropicAI How does one use someone else's sauce and then have it taste better?

We ran internal benchmarks comparing @OpenAI's GPT 5.6 Sol vs @AnthropicAI Claude Fable 5 GPT 5.6 Sol performs on-par with Fable at a lower cost, but how it does this is fascinating. GPT 5.6 spends MORE time and tokens gathering context and less on formal planning before executing. This a stark contrast to previous GPT Codex models that would spend significantly less time gather context compared to Claude models. It highlights the importance and impact of context gathering for coding agents. Better context, better outputs. It seems like @OpenAI may have finally found out Claude's secret sauce.

@zeeg the lights are critical

SF founders: show me your keyboard game

@adelbucetta @hwchase17 @BraceSproul It’s one a piece of agent memory, but not the whole

@hwchase17 @BraceSproul @devstein64 what people often miss is that llm wikis are just a stepping stone true agent memory will be more like a curated, context-aware knowledge graph that's updated in real-time, not just a static collection of notes

llm wikis are a glimpse of the future of what agent memory looks like this blog i wrote resonated with a lot of folks will be discussing this (as well as some updates ive made to my beliefs since this!) this thursday with @BraceSproul @devstein64 events.langchain.com/webinar/llm-wi…

@adelbucetta @hwchase17 @BraceSproul depends on the implementation!

@hwchase17 @BraceSproul @devstein64 wikis just provide the illusion of memory, don't they? still have to figure out how to update and synthesize that knowledge in production

🚨Emergency webinar: LLM Wikis and how to give your agent memory LLM Wikis are so hot right now - OpenWiki by @BraceSproul up to nearly 7k GitHub stars in less than a week I'll be chatting with Brace and @devstein64 about Wikis this Thursday: events.langchain.com/webinar/llm-wi…

@onlydole 🙇‍♂️

Come join us on Thursday! It'll be a great session you'll want to add to your MEMORY.md 😄

🤫

@BraceSproul @hwchase17 to wiki or not to wiki 🧐

We're going to be discussing LLM memory & wiki's this week with @hwchase17 and @devstein64! Don't miss it

@tcballard @BraceSproul @hwchase17 relevant - will check it out 👀

@BraceSproul @hwchase17 @devstein64 You should do a bit on the rac-spec itsthelore.github.io/rac-spec/why-s…

does your agent need a wiki? should humans and agent use the same wiki? should you have one wiki or many wikis? if you're wiki-curious, join @BraceSproul @hwchase17 and I on Thursday! you don't want to miss it @dosu_ai 🤝 @LangChain

@learn_ai_daily @hwchase17 @LangChain @BraceSproul you're assuming everyone on the webinar is pro Wiki 😉

@hwchase17 @LangChain @BraceSproul @devstein64 Not sure if this will stick lol

@zeeg goals

One of my absolute favorite podcasts, and absolute favorite partners

i feel like the divide of good engineering is getting larger, and way more visible

✍️

@zeeg can do a snapshot for pre/post Nov 2025

Too bad the top N lists these days mostly showcase who can produce the most slop. Rip when 10k contributions was peak productivity.

majority of these commits were handmade