GPT-5 just refactored my entire codebase in one call. 25 tool invocations. 3,000+ new lines. 12 brand new files. It modularized everything. Broke up monoliths. Cleaned up spaghetti. None of it worked. But boy was it beautiful.

A bit sad how the GPT-5 launch is going so far, especially after the long wait and high expectations - The automatic switching between models (the router) seems partly broken/unreliable - It's unclear exactly which model you're actually interacting with (standard or mini, reasoning level, old/new) - Router issues probably contribute to many negative first impressions ("GPT-5 is bad"), especially when you can't easily tell which model is handling your requests - e.g. GPT-5 Thinking performs better at writing compared to standard GPT-5 ("think harder" prompts might also help) - I'm seeing lots of complaints about legacy models being removed and usage limits for Plus (and also Free) accounts ("bring back 4o, o3, ...") - Context window lengths aren't clear, nor how many and which exact GPT-5 models ChatGPT uses (standard, mini, new, old) - no indicator of which model is active at any moment - The gradual rollout and current capacity constraints add to confusion, because not everyone can access the new models yet - Mixed-up charts during the livestream provided plenty of free material for chart-crime and vibe-charting posts, which hasn't helped build trust or confidence - And of course, the community had extremely high expectations across all fronts and modalities, as usual I'm hoping improvements in the next hours/days, and today's AMA, can clarify some of these open issues and questions

GPT-5 i utgangspunktet one-shot dette

Gpt - 5 Tenker, ett skudd vibe-koding: Space sim, meditasjonsapp, duo-lingo-klon, Windows 95

Tidlig GPT-5-anmeldelse: • Best i klassen som chat-bot • UVIRKELIG for prisen • Rent kodeperspektiv Claude Code er fortsatt konge for øyeblikket Jeg ba begge om å bygge meg et personlig operativsystem i stil med Matrix. GPT5 til venstre, Claude til høyre Vinneren er klar

En samling av erfaringer jeg gjorde med GPT-5 i ett skudd. Diktkameraappen er spesielt imponerende fordi modellen kom opp med alle detaljene, som måten bildene stables på i galleriet, fotofremkallingsanimasjonen osv

For mindre enn 29 timer siden droppet OpenAI GPT-5. Og noen kaller det den beste modellen. Noen ikke så mye. 10 ville eksempler:

Grok 4 mot GPT-5 Det er ikke engang i nærheten. Grok 4 Auto-modus fungerer ekstremt bra, den svarte på dette enkle matematiske spørsmålet på ~1 sek uten å måtte bytte modell.