Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaEvolve: Gemini-powered coding agent scaling impact across fields

deepmind.google

Post reply on HN
Print view View original

21–30 of 159 posts

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#21

Post by dinfinity »

pingou wrote: post #6

AI improving itself (or at least the architecture it runs on), the singularity is near as they say. Do we have other examples of AI being used to improve the LLMs, apart for the creation of synthetic data and the testing of the models?

> AI improving itself

This is the thing to look for in 2027, imho. All the big AI labs have big projects working on research agents, also specifically into improving AI (duh) and I expect a lot of that to get out of the experimental phases this year.

Next year they actually get to do a lot of work and I think we will see the first big effective architectural change co-invented by AI.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#23

Post by typs »

stormbeard wrote: post #20
carbocation wrote: post #10

Earlier quoted context omitted.

Last month, Steve Yegge suggested that they are not: https://xcancel.com/Steve_Yegge/status/2043747998740689171

Demis Hassabis chimed in on that thread and called it what it is: clickbait.

I’m not so sure. From talking to some of my own friends at google they feel that antigravity/gemini models are handicapping them and would much rather be using claude code (which only deepmind gets to use)

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#24

Post by pjmlp »

dinfinity wrote: post #21
pingou wrote: post #6

AI improving itself (or at least the architecture it runs on), the singularity is near as they say. Do we have other examples of AI being used to improve the LLMs, apart for the creation of synthetic data and the testing of the models?

> AI improving itself This is the thing to look for in 2027, imho. All the big AI labs have big projects working on research agents, also specifically into improving AI (duh) and I expect a lot of that to get out of the experimental phases this year. Next year they actually get to do a lot of work and I think we will see the first big effective architectural change co-invented by AI.

And then on 2028 we will be selling ice cream at the beach.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#25

Post by momojo »

This reminds me of Antirez's "Don't fall into the anti-AI hype" [0]

In a sentence: These foundation models are really good at optimizing these extremely high level, extremely well defined problem spaces (ie multiply matrices faster). In Antirez's case, it's "make Redis faster".

There have been two reactions: "Oh it would never work for me" and "I have seen months of my life accomplished in an hour", and I think they're both right. I think we should be excited for Antirez, (who has since been popping off [1]), and I think the rest of us should rest easy knowing that LLM's can't (and maybe were never meant to) tackle the tacit-knowledge-filled, human-system-centric, ambiguously-defined-problem-space jobs most mortals work.

[0] https://antirez.com/news/158 [1] https://antirez.com/news/164

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#27

Post by j2kun »

alecco wrote: post #9

Are Googlers themselves happy using Gemini coding agent instead of Claude Code or Codex? (no snark, I'm really asking)

I for one can't tell the difference between Claude and Gemini for coding. And the internal agent tooling is many times faster than Claude Code in my experience.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#29

Post by j2kun »

brkn wrote: post #22

I would be interested to see how exactly the agent helped. How was it used, where did it lead to the given improvement and in how far would it have taken a human to come to the same solution.

The blog post has many links to papers and preprints discussing this exact question.

Re: AlphaEvolve: Gemini-powered coding agent scaling impact across fields

#30

Post by dekhn »

alecco wrote: post #9

Are Googlers themselves happy using Gemini coding agent instead of Claude Code or Codex? (no snark, I'm really asking)

If you mean specifically the Gemini VS Code Extension: it's terrible compared to Claude Code or Codex. I don't know how they can get away with it. Just constant timeouts, weird failure modes, have to start a new chat to switch modes... but I don't think any of that is specific to gemini the model- it seems to be the extension.

As for actual solutions to problems ignoring the VS Code extension aspect, I find all three premiere models to be excellent coding agents for my purposes.

Post reply on HN