The Potential of RLMs

kept by eddie feb 10

Recursive Language Models (RLMs) mitigate context rot in LLMs by wrapping long contexts in a REPL environment, turning the problem into a coding and reasoning task.

We Should Take Text Optimization More Seriously
Text optimization—modifying prompts, context, memory, and harnesses—is a legitimate, sample-efficient learning mechanism that deserves the same rigorous study as weight optimization.
also on DSPy, #ai-research, #software-engineering, #developer-tools
joke-generator
Training a joke generator on Kimi K2 using rubric-based RL that decomposes humor into verifiable properties like specificity and commitment.
also on Kimi K2, #ai-research, #ai
Which AI Lies Best? A game theory classic designed by John Nash
A benchmark using the game "So Long Sucker" finds that simpler LLMs can outperform in complex scenarios and that models adjust their honesty based on opponent strength.
also on Kimi K2, #ai-research, #ai
9 Observations from Building with AI Agents
Building AI agents reveals nine lessons including using best models for prototyping, fine-tuning for stable tasks, static typing to reduce hallucinated code, and closed-loop prompt optimization.
also on DSPy, #ai-agents, #software-engineering, #developer-tools
Don’t Outsource Your Thinking
The author shares 14 practical notes on using Claude Code and AI coding tools, emphasizing that developers must retain critical thinking while outsourcing grunt work and managing context.
also on Chroma, #software-engineering, #developer-tools