Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB
by 8note on Saturday December 21, 2024 @03:40PM
(#42482134)
> deterministic generation
what are you using for deterministic generation? the last i heard even with temperature=0 theres non determinism introduced by float uncertainty/approximation
Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB
by exhaze on Sunday December 22, 2024 @03:00AM
(#42485001)
Hey, that's a great question. I should have been more clear: for deterministic generation that's not done using an LLM. It's done using just regular execution of TypeScript. The code generators that were created using an LLM and that I manually checked for correctness, they're the ones that are generating the other code - most of the code. So that's where the determinism comes in.
Your concerns about mysterious AI code and system crashes are backwards. This approach eliminates integration bugs and maintenance issues by design. The generated TypeScript is readable, fully typed, and consistently updated across the entire stack when business logic changes.
If you're struggling with AI-generated code maintainability, that's an implementation problem, not a fundamental issue with code generation. Proper type safety and schema validation create more reliable systems, not less. This is automation making developers more productive - just like compilers and IDEs did - not replacing them.
The code works because it's built on sound software engineering principles: type safety, single source of truth, and deterministic generation. That's verifiable fact, not speculation.