Tokenbender says AI failures are starting to feel “strangely inhuman”
tokenbender · x · 2026-07-21
Tokenbender says model mistakes are starting to feel “strangely inhuman”
The post quotes tokenbender reacting to Casey Handmer’s complaint that Grok 4 can solve Physics Olympiad-style problems yet still miss core insight.
The takeaway is not a benchmark claim but a cultural one: as models get better on formal evals, their failures may increasingly feel more alien, not less. The attached screenshot turns that into a meme about “the mistakes seem to be strangely inhuman.”
Related event: AI Models Show 'Inhuman' Blind Spots Despite Skills(2 posts)→
More from Fun
- Meme: ML researchers refuse the real world — 'iid data only for me, thanks' — miniapeur · 2026-10-27
- Meme: Modern PCs cry over 0.1 dB while chad users shrugged at jet-engine boot noise — miniapeur · 2026-10-27
- Gary Marcus mocks being blocked mid-debate: 'Very courageous!' — GaryMarcus · 2026-10-27
- Blogger plans to use Grok to auto-block AI comment bots on X — vista8 · 2026-10-27
- Anthropic files S-1 on Monday morning, VCs complain they can't do instant teardowns — mattturck · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27