Re:GPT-5.3-Codex
by freakynit on Friday February 06, 2026 @05:08AM
(#46911042)
I think this all comes down to information.
Most prompts we give are severely information-deficient. The reason LLMs can still produce acceptable results is because they compensate with their prior training and background knowledge.
The same applies to verification: it's fundamentally an information problem.
You see this exact dynamic when delegating work to humans. That's why good teams rely on extremely detailed specs. It's all a game of information.
Re:GPT-5.3-Codex
by adrianN on Friday February 06, 2026 @12:32PM
(#46915695)
Having prompts be information deficient is the whole point of LLMs. The only complete description of a typical programming problem is the final code or an equivalent formal specification.
Most prompts we give are severely information-deficient. The reason LLMs can still produce acceptable results is because they compensate with their prior training and background knowledge.
The same applies to verification: it's fundamentally an information problem.
You see this exact dynamic when delegating work to humans. That's why good teams rely on extremely detailed specs. It's all a game of information.