Anthropic system card chart shows internal model beating public Claude models, joked poster
felpix_ · x · 2026-11-10
An X post shares a chart attributed to an Anthropic system card comparing Claude Opus 5, Claude Myths 5.1/5.2 and other models, where an "Internal model" outperforms the released ones. The quoted tweet jokes about the card's casual tone — "this one isn't the best, and the better one only took 2 weeks longer to make." Note: the "Myths" model names are unverified.
More from Fun
- Dev builds a playable browser game with Claude Fable 5.2: sail through 8 dream worlds — FinanceYF5 · 2026-11-10
- Claude builds a 500,000-tile mosaic engine, sparking the 'tasteslop' debate — teortaxesTex · 2026-11-10
- 'Everyone asks who is Jensen Huang, nobody asks how is Jensen Huang' — ns123abc · 2026-11-10
- 2013 AAA game visuals still out of reach for AI-generated Fable, dev argues — rms80 · 2026-11-10
- Users Complain Claude Refuses Oxford Comma, Twisting Sentence Meaning — eschadiol · 2026-11-10
- slop-review: a GitHub Action that fights AI slop PRs with meaningless AI reviews — heyneighbor · 2026-11-10