why dspy usually wastes your time (and when it doesn't) the question: "should i use dspy for prompt optimization? it seems like the perfect tool for improving my rag system." the answer: dspy is great for very specific, well-defined tasks. but for most rag systems, it's a

What if scaling the context windows of frontier LLMs is much easier than it sounds? We’re excited to share our work on Recursive Language Models (RLMs). A new inference strategy where LLMs can decompose and recursively interact with input prompts of seemingly unbounded length,

Research assistant framework using LLMs to search and summarize

BREAKING: Amazon’s, $AMZN, robotics team is working towards automating 75 percent of the company’s entire operations, per the Verge

An early look at what people are building with Claude Skills:

👀 Animals have been assigned. Scheduled to print fall 2026! We have iterated on this with over 3k students (and continue to do so). We give our students access to the full draft as part of our evals course (link in bio).

Andrej Karpathy Epic Nano Banana Pro workout plan, Andrej Karpathy! I animated it with Grok AI to make it pop even more—dynamic transitions for that extra testosterone boost on Tuesday 💪. What tweaks would you add next? #NanoBananaPro #GrokAI #AI Fitness

Quick new post: Auto-grading decade-old Hacker News discussions with hindsight I took all the 930 frontpage Hacker News article+discussion of December 2015 and asked the GPT 5.1 Thinking API to do an in-hindsight analysis to identify the most/least prescient comments. This took

Here's a collection of useful patterns I've found after vibe-coding 150 different single-file HTML tools over the past couple of years simonwillison.net/2025/Dec/10/ht…

OpenSkills v1.3.0 is out 🚀 The Universal Skills loader for AI Coding Agents Now you can: • Use Symlinks with your skills • Install skills from local paths & private git repos • Sync to any .md file (--output flag) • Run fully headless in CI/CD (--yes) npm i -g openskills

new blog post - i hate DSPy and i'm tired of pretending i don't - trying to implement GEPA turned me into the joker - it's mostly my fault but there are some interesting takeaways link below :)

To solve long-running agents, one must first solve context compression. We evaluated compaction/compression strategies from OpenAI, Anthropic, and Factory on 36,000+ messages from real agentic software development sessions.

I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become

We just dropped the technical report of AI-Trader🚀 - the fully autonomous trading benchmark where AI agents make real financial decisions without any human help. Check out our technical report to see how we built this systematic framework and witness the battle between leading

Here you can see how I've set up my self-hosted AI code review. Decided to use pi coding agent for code review (by Mario Zechner). Wit this setup I can - swap models anytime (claude, gemini, glm ...), - set my own reviewer prompts (adjusted to my codebase), - stay within

📢 Confession: I ship code I never read. Here's my 2025 workflow. steipete.me/posts/2025/shi…

🚀 Our lab just open-sourced DeepTutor - AI-Powered Personalized Learning Assistant We're actively exploring how agentic AI can assist students and researchers throughout their learning process. DeepTutor brings together research, problem-solving, practice generation, and

今天都在谈 Manus 被 Meta 收购，我讲点小故事，给创业者们看看什么叫顶级判断力和决断力。

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to

看到越来越多的公司基于 claude code 开发自己公司研发工作流： github.com/EveryInc/compo…