Astra's Post-Training Is Far From Done: More Compute Doesn't Monotonically Help Yet
teortaxesTex · x · 2026-09-04
teortaxesTex notes several Astra benchmark charts reflect the same phenomenon: its post-training is far from finished — the model doesn't yet reliably or monotonically convert more compute into better results, suggesting this skill hasn't been trained in yet.
Related event: OpenAI Launches GPT-6 Astra, Declaring the AGI Era(388 posts)→
More from Models
- Mistral's Voxtral 3 speech models land #3 on STT leaderboard at $13/1M chars — ArtificialAnlys · 2026-10-21
- AI2's FairStress benchmark exposes hidden fairness asymmetries across 11 open-weight models — allen_ai · 2026-10-21
- Perplexity ships Decider V1.2, tops Vals AI's new ClaimBench decision-model benchmark — bo_wangbo · 2026-10-21
- Omnii-1 genome model debuts: first AI-designed phages ever given to a human patient — JosephJacks_ · 2026-10-21
- Nous Portal Pricing Revealed: Unused Credits Roll Over, Up to $100 Cap on $200 Tier — alexcovo_eth · 2026-10-21
- 1.3B open-source doc parser OXR tops three benchmarks, parsing 100 pages in 101 seconds — s_mohinii · 2026-10-21