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
- Creator's 2566-rated champion bot dethroned on Arena Ladder, training a comeback version — tristanbob · 2026-10-27
- Procedural floral borders bring illuminated-manuscript aesthetics to the web — round · 2026-10-27
- Viral satirical job hack: fake your MRR, farm impressions, wait for offers — _jaydeepkarale · 2026-10-27
- Musk builds a Neo cloud while declaring his competition 'going to zero' — tekbog · 2026-10-27
- Tesla flies away from a police stop in a hilariously convincing Dreamina AI video — EvenWrangler-6577 · 2026-10-27
- Interactive pixel-art portfolio built entirely with Claude Opus 5.5 — CatAstro_Piyush · 2026-10-27