The Problem is Prompt Debt

kept by eddie jun 24

Hand-tuning natural language prompts for AI systems accumulates debt that slows iteration, locks teams to one model, and should be replaced with metrics, tests, and automated prompt optimization.

optimize_anything: A Universal API for Optimizing any Text Parameter - GEPA
GEPA's optimize_anything API optimizes any text-representable artifact (code, prompts, agent architectures) and achieves state-of-the-art results across eight domains, matching or beating domain-specific tools.
also on GEPA, Claude Code, #software-engineering, #ai, #developer-tools
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, #machine-learning, #software-engineering, #developer-tools
The Potential of RLMs
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.
also on DSPy, #software-engineering, #ai, #developer-tools
[2601.02439] WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
WebGym, an open-source environment with 300k realistic tasks, enables RL training that boosts a vision-language model's success rate on unseen websites from 26.2% to 42.9%.
also on GPT-4o, #machine-learning, #ai
I Tried to Make AI Writing Sound Human by Banning AI Words Through logit_bias - Vincent Schmalbach
The author applied logit_bias to penalize AI‑common tokens, observing a roughly one‑third reduction in those words while sacrificing one acceptable rewrite out of eight.
also on GPT-4o, #software-engineering, #ai, #developer-tools