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
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Agile co-author Ron Jeffries publishes 'Resist AI', urging developers to push back — mborch · 2026-09-11