Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)ZB
Posts
0
Comments
715
Joined
1 yr. ago

  • Talking about Alpha Evolve https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/ ?

    First, Microsoft isn't using this yet but even if they were it doesn't work in this context. What Google did was they wrote a fitness function to tune the Generative process. Why not have some rubric that scores the code as our fitness function? Because the function needs to be continuous for this to work well, no sudden cliffs. But also they didn't address how this would work in a multi-objective space, this technique doesn't let the LLM make reasonable trade offs between complexity and speed.

  • The point is to get open source maintainers to further train their program because they already scraped all our code. I wonder if this will become a larger trend among corporate owned open source projects.

  • It's important to understand that any argument against improving one's material conditions is going to be rightfully ignored. Better to point out that without removing the yoke of power, any concessions can be easily removed.

  • I've deployed LangChain to production shudders. My use case involved sending images results back to the "agent" and that use case is an after thought for many of these services. I ended up extending the Gemini Vertex client to fake it. The artifacts system is basically pass around a dictionary and pray both ends agree on the shape.

    This is not an endorsement of LLMs in general. I'm working to replace it with a decision tree.