Agentic OS and Self-Improvement Experiments
Ghost_Pilot_MD · x · 2026-07-15
The post recaps a discussion on agentic systems: AIDE² is described as enhancing the "agent operating system" layer, while GoalOS attempts to elevate and govern the overarching OS of an "agentic institution."
A cited reference highlights a specific experiment: researchers allowed the system to conduct self-research/automated research. After 8 consecutive days, its performance on a held-out test set surpassed a manually tuned harness that took two years to optimize, which is being called the "first experimental evidence of Recursive Self-Improvement (RSI)."
Related event: AIDE² Self-Improvement Run Beats 2 Years of Manual Tuning(12 posts)→
More from coding & agent
- Design Is Becoming Game Dev: Build Your Own Tools With AI as the Executor — hewarsaber · 2026-10-27
- Dev turns DJI Mavic into local AI security drone built with Opus 5.5 — alexcovo_eth · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27