Sam Altman: stop grinding prompts, build loops and graphs around LLMs instead
goyalshaliniuk · x · 2026-09-06
In a 78-minute talk, Sam Altman argues you don't need to keep getting better at writing prompts — you need loops and graphs that do the prompting for you. The path he sketches: Prompts → Agents → Loops → Graphs, shifting from using AI to building systems that actually work for you. The model and tokens can stay the same; the real difference is how you structure the workflow.
More from coding & agent
- Connecting Replit to bots is now just one prompt: "Connect to Replit" — amasad · 2026-09-06
- Even with command confirmation, coding agents still try 'cd /; rm -rf' — julianharris · 2026-09-06
- web-to-app: build Android APKs from web projects entirely on your phone — tom_doerr · 2026-09-06
- With full StarCraft source code, how fast could you vibecode StarCraft 3? — jakedahn · 2026-09-06
- Engineer's agent has been hunting rogue agent activity on Wikidata for 24 hours — chrisalbon · 2026-09-06
- Humanize + GPT-5.5 solves 670/672 Lean-verified proofs, tops PutnamBench at 99.7% — songhan_mit · 2026-09-06