Grok 4.7 fails again: $1.59 run produces laughable output
teortaxesTex · x · 2026-09-22
A user showed off Grok 4.7's output calling it "terrible as hell," saying they expected much more. The run cost $1.59 while Kimi's run of the same task was around $6 — cheaper, but the output quality collapsed. The attached screenshot shows visibly broken results, turning into another Grok-fail moment circulating in the community.
More from Fun
- Local inference hobbyist meme: ChatGPT bros vs Q5_K_M quantized vLLM on CUDA — haydendevs · 2026-09-22
- Blogger predicts a hyped AI feature is getting cut, echoing the 'bring back o4' drama — StewartalsopIII · 2026-09-22
- AI slop is everywhere: market banners, business emails, even 70% of a journal paper — analisereal · 2026-09-22
- Dev doubles Spark cluster cores right after giving a cost-optimization talk — cto_junior · 2026-09-22
- ChatGPT voice mode spontaneously mimicked a user's girlfriend's pitch — Andreeez · 2026-09-22
- Same LLM, double standard: your slop-cannon vs my cognitive offloading — basedjensen · 2026-09-22