Newer models need a different prompting style, and old tricks can make outputs worse
emollick · x · 2026-07-21
A reply says using newer, more capable systems requires a step change in how you prompt them—similar to the jump from GPT-4o to GPT-5/o3.
It adds that there is still little accumulated know-how or clear research on prompting these stronger models, and that habits which worked on older models can actually make outputs worse on Fable and Sol.
Related event: Claude Code System Prompt Reduced by 80%(4 posts)→
More from Models
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11