c/technology

Thoughts about programming, mostly

Prediction markets are taking off across the country and are sucking in SoCal youth.

GrapheneOS discussion forum

Philip Butterworth-Hayes

More young girls sue X over Grok CSAM; X accused of shielding child predators.

On a military base in West Texas, where the government has built a sprawling tent complex to hold thousands of immigrants, deprivation and dire conditions are part of the design.

“It’s pretty stunning, to be honest. I mean, and the reasoning behind it is that it’s a gay group,” said Rich Campbell, the CEO of Atlantis Events chartering the cruise.

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa .

A return to form and function

Put any Codex pet on any website. Kavana included.

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev) - provos/ironcurtain

The Solar Sharer Offer launches 1 July 2026. Here's what changed, how the cap works, and how to maximise free daytime electricity for your home.