A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model.

Added to korrents 27 Jul 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Open-source models cannot keep frontier systems in check, because they will always be much dumber than the frontier. ACAjeya Cotra1 Sept 2026similar wording
• Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more. BCBoris Cherny27 Jul 2026similar wording
• At any given moment the frontier systems are the ones worth worrying about, because by the time open models can do what these agents did, frontier models will be doing something far worse. ACAjeya Cotra1 Sept 2026similar wording
• Frontier models must be cheap enough for anyone to use, because a world in which they are rationed to the wealthiest developers is the wrong world. AWAlexandr Wang29 Jul 2026similar wording
• You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance. BCBoris Cherny27 Jul 2026similar wording

See this on the map →