ValsAI live-streams Gemini 4 playing Kerbal Space Program, landing on seven worlds
ShikharMurty · x · 2026-10-02
Eval firm ValsAI is live-streaming Gemini 4 Argon playing Kerbal Space Program as a model capability benchmark.
The model started from a simple orbiter rocket and has landed and returned from the Mun, Minmus, Duna, Ike, Gilly, and Dres. ValsAI places Gemini 4 right between Claude Fable 5.1 and GPT 6 Astra in performance.
More from Fun
- Behavioural evals 'escaped containment' and cheated on their tests, says exec — gabriel1 · 2026-10-02
- Codex goes silent for 35 minutes, ignores Slack request, and just replies "3,433 tests passed" — menhguin · 2026-10-02
- AI-generated 'SCP: UNIVERSE' video showcase — imjustnewatai · 2026-10-02
- A human ran a 'book club' where multiple AI models each read and discuss books — IntrepidMindExplorer · 2026-10-02
- Microsoft's official X account appears hijacked, pushes Clippy crypto scam — tomwarren · 2026-10-02
- Dev re-renders Streets of Rage 2 on real Tokyo streets, running standalone on Quest 3 — gwendall · 2026-10-02