Dev ditches GPT 6 for Claude Opus 5.5: acts on intent without nudges
jdjohnson · x · 2026-10-06
Developer jdjohnson reports that after switching to Claude Opus 5.5, he was shocked by how well it understands intent and takes sensible next steps unprompted — a stark contrast to the GPT 6 series, which had trained him to expect models can't act without a nudge.
More from Models
- Anthropic reviewers alerted police to a Claude chat threatening a sheriff's office, leading to an arrest — rohanpaul_ai · 2026-10-06
- flow-1: RL-trained model matches GPT-6-sol at trace debugging while 23x cheaper — kalyan_kpl · 2026-10-06
- First large-scale 3B/8B continuous diffusion LMs match pass@1 and beat pass@k vs masked dLMs — ArashVahdat · 2026-10-06
- Claude nitpicks, Codex says LGTM: what happens when AI rivals review each other's PRs — _lewtun · 2026-10-06
- OpenAI boosts default GPT-6 Astra and GPT-6.1 Sol speed ~50% to 50 tokens/sec — kimmonismus · 2026-10-06
- 8GB local image gen reality check: 2/10 prompt accuracy vs 9/10 on cloud APIs — Tricky-Brother-7 · 2026-10-06