ValsAI launches RSI Index, first third-party benchmark measuring how close AI is to self-improvement

JenniferHli · x · 2026-09-11

ValsAI introduces the RSI Index

• Driven by concerns about recursive self improvement, AI safety is back in the spotlight.
• ValsAI, in collaboration with marimoio and CoreWeave, built the first third-party benchmark measuring how close AI is to building its own successor.
• The benchmark runs every frontier model through the same AI research tasks and scores each against the strongest published human results.
• Early finding: models can do the work, but are still far from the human frontier.

Original post →

More from Models

• DeepSeek Flash impresses: non-sycophantic, argumentative, and blazing fast — oran_ge · 2026-09-11
• Gemini glitches into endlessly spamming the word 'shame' — tugkanintassagi · 2026-09-11
• Early take: DeepSeek V4.1 Solo beats Agent Teams and GLM 5.3 Flash on quality and cost — teortaxesTex · 2026-09-11
• What counts as an 'exchange'? Anthropic's 865K/day metric questioned — teortaxesTex · 2026-09-11
• OpenAI reportedly aims its new internal model at Riemann and P vs NP — zephyr_z9 · 2026-09-11
• MLX vs CUDA: Qwen 3.8 Flash Next optimization duel delivers 55%+ speedups on both sides — gajesh · 2026-09-11

Models channel →