Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

>LLMs using code to answer questions is nothing new, it's why the "how many Rs in strawberry" question doesn't trip them up anymore, because they can write a few lines of Python to answer it, run that, and return the answer.

False. It has nothing to do with tool use but just reasoning.



What is reasoning?

I also can not multiply large numbers without a paper and pencil, and following an algorithm learned in school.

That is the same as an LLM running some python, is the same as me following instructions to perform multiplication.


It's so easy to google this and find that they all do exactly this.

Gemini: https://ai.google.dev/gemini-api/docs/code-execution

ChatGPT: https://help.openai.com/en/articles/8437071-data-analysis-wi...

Claude: https://claude.com/blog/analysis-tool

Reasoning only gets you so far, even humans write code or use spreadsheets, calculators, etc, to get their answers to problems.


you have just linked the fact that they have code executions but not proved that it is needed for strawberry problem.

there are multiple ways to disprove this

1. GPT o1 was released and it never supported the tools and it easily solved the strawberry problem - it was named strawberry internally

2. you can run GPT 5.2-thinking in the API right now and deny access to any tools, it will still work

3. you can run deepseek locally without tools and run it, it will still work

Overall this idea that LLM's cant reason and need tools to do that is misleading and false and easily disproven.


Oh right you're very focused on specifically the strawberry problem. I just gave that as a throwaway example. It's a solution but not necessarily the solution for something that simple.

My point was much more general, that code execution is a key part of these models ability to perform maths, analysis, and provide precise answers. It's not the only way, but a key way that's very efficient compared to more inference for CoT.


I agree that tool usage dramatically improves the utility of LLM's. But it is absolutely not needed for the strawberry problem.

It can perform complicated arithmatic without tools - multiplying multiple 20 digit numbers, division and so on (to an extent).




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: