← Back to context

Comment by sebzim4500

4 days ago

Unless I'm misunderstanding what you are asking the model to do, Gemini 2.5 pro just passed this easily. https://g.co/gemini/share/e2876d310914

As I mentioned, this is not a scientific test but rather just something that I have tried from time to time and has always (shockingly in my opinion) failed but today worked. It takes a minute of two of prompting, is boring to verify and I don't remember exactly which models I have used. It is purely a personal anecdote, nothing more.

However, looking at the code that Gemini wrote in the link, it does the same thing that other LLMs often do, which is to assume that we are encoding individual long values. I assume there must be a github repo or stackoverflow question in the weights somewhere that is pushing it in this direction but it is a little odd. Naturally, this isn't the kind encoder that someone would normally want. Typically it should encode a byte array and return a string (or maybe encode / decode UTF8 strings directly). Having the interface use a long is very weird and not very useful.

In any case, I suspect with a bit more prompting you might be able to get gemini to do the right thing.

  • I think it's because the question is rather ambiguous - "convert the number to base-N" is a very common API, e.g. in C# you have Convert.ToString(long value, int base), in JavaScript you have Number.toString(base) etc. It seems that it just follows this pattern. If you were to ask me the same question, I'd probably do the same thing without any further context.

    OTOH if you tell it to write a Base62 encoder in C#, it does consistently produce an API that can be called with byte arrays: https://g.co/gemini/share/6076f67abde2

    • There is Convert.ToBase64String so I don't think encode is necessarily universal (though probably more precise).

  • Similarly, many of my informal tests have started passing with Gemini 2.5 that never worked before, which makes the 2025 era of AI models feel like a step change to me.

I’ve been using Gemini 2.5 pro side by side with o1-pro and Grok lately. My experience is they each randomly offer significant insight the other two didn’t.

But generally, o1-pro listens to my profile instructions WAY better, and it seems to be better at actually solving problems the first time. More reliable.

But they are all quite similar and so far these new models are similar but faster IMO.