MuscleMemory is an open-source procedural memory system that watches AI coding agents and captures repeatable, successful workflows as reusable "skills." It records which files were changed, the final passing test command that proves the fix, and contextual warnings for partial matches. A skill is only accepted after two independent successful reproductions and human approval via a dashboard; a single subsequent failure disables the skill and failed attempts are stored as "watch out" notes. The system is local by default (SQLite and a small on-device model) with an option for PostgreSQL + pgvector for teams, and integrates with Codex, Claude Code, Cursor, CleanSlate, an MCP API and Python/TypeScript SDKs.
Benchmarks show concrete gains: in controlled Codex sessions MuscleMemory reduced input tokens by 25.5%, tool calls by 30.4% and elapsed time by 28.2% while preserving successful outcomes; other runs reported up to 43.5% token reduction. Installation is straightforward (pipx install, init, start, connect) and a dashboard lets maintainers inspect, approve, export (SKILL.md) and manage skills. Command normalization, bounded file checks and strict trust rules prevent unsafe replay. The project is Apache‑2.0 licensed, tested but early-stage, and notes limits such as benchmark scope and untested cross-repository recall.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
AI founders and executives in San Francisco discussed rapid revenue growth, data brokerage, and the evolving AI landscape, emphasizing the importance of data and model flexibility. They highlighted the potential of autonomous agents, the significance of data valuation, and ongoing reverse engineering efforts in the industry. (twitter.com)
Geoffrey Hinton warns that AI is creating alien-like beings and we have only a few years to adapt to this reality. He criticizes Donald Trump's understanding of superintelligence and emphasizes the need to prioritize human interests. (theguardian.com)
Anthropic suggests its AI may possess consciousness, raising ethical questions about AI feelings and suffering. The development has sparked debate among tech leaders about the moral implications and safety risks of advanced AI systems. (bbc.com)
Self-Evolving Agent Harness revises an AI agent's software components through a feedback-driven process, while keeping model weights fixed. It formalizes continuous validation and updates to improve reliability, safety, and organizational workflows. (arxiv.org)
Reinforcement learning in large language models can cause 'thinking leakage,' where models partially reactivate their original reasoning abilities rather than learning new behaviors. This leakage explains much of the observed performance improvements in models trained with RL in non-thinking modes. (arxiv.org)
Sergey Brin states that Google's AI models are entering a phase of recursive self-improvement, where AI helps develop better AI systems. This process could accelerate AI development significantly within the next year, according to industry experts. (businessinsider.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.