GPT-6 Astra called 'rough launch but feels better than benchmarks' — community claps back
ns123abc · x · 2026-09-04
Defending OpenAI's newly released GPT-6 Astra, one user argued that like GPT-5, it had a rough launch and a few questionable benchmark scores, but feels better to use than the benchmarks suggest, and sentiment will improve as more people try it.
The take drew mockery: "bro you don't even have access yet" — capturing the perennial benchmarks-vs-experience debate and the tension around scarce early access.
More from Fun
- GPT-6 built a full macOS simulator in under 75 minutes, stunning the panel — thursdai_pod · 2026-09-04
- Immunologist one-shots a 5-minute T-cell lecture video from a single prompt with GPT-6 — DeryaTR_ · 2026-09-04
- All AI models down: dev forced to open tmux + vim for a 1000-line AI PR — generativist · 2026-09-04
- AI meme reimagines Claude 3 Opus as a barista serving Dario Amodei — repligate · 2026-09-04
- "Prompting is dead, long live prompting" — the debate in one line — BLUECOW009 · 2026-09-04
- Meme: asking Claude mid-kernel-writing what pre-training felt like — shauseth · 2026-09-04