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

111–120 of 159 posts

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

#111

Post by poisonfountain »

Yokohiii wrote: post #107
Yokohiii wrote: post #91

Earlier quoted context omitted.

Such invasive practices are pretty disgusting. But I don't think it will be pervasive. Once it spreads, AI vendors and abusive companies will be hold accountable. There is also an obvious conflict, the surveillance will likely be very selective. Programmers have to record everything, while middle managers have a choice to sign off everything. Senior management will of course do whatever but have full insight on the d…

thanks for the downvote anon. its an convenient conversation.

I disagree but it wasn't me who downvoted, just so you know.

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

#113

Post by Yokohiii »

poisonfountain wrote: post #111
Yokohiii wrote: post #107

Earlier quoted context omitted.

thanks for the downvote anon. its an convenient conversation.

I disagree but it wasn't me who downvoted, just so you know.

Yeah I wasn't accusing you. Was likely that you disagree, I can deal with that.

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

#114

Post by Yokohiii »

charleshn wrote: post #106
Yokohiii wrote: post #62

Earlier quoted context omitted.

This is just a flex post. Be a billion dollar company or get out.

They'll likely make it available at some point, but for now one can use OpenEvolve [0] which is not quite as good but should be a good start to use the same LLM-driven evolutionary framework. [0] https://github.com/algorithmicsuperintelligence/openevolve

Your link seems completely unrelated. Why would you suggest that?

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

#115

Post by charleshn »

Yokohiii wrote: post #114
charleshn wrote: post #106

Earlier quoted context omitted.

They'll likely make it available at some point, but for now one can use OpenEvolve [0] which is not quite as good but should be a good start to use the same LLM-driven evolutionary framework. [0] https://github.com/algorithmicsuperintelligence/openevolve

Your link seems completely unrelated. Why would you suggest that?

Not sure what you mean: OpenEvolve is an open source implementation of AlphaEvolve: https://huggingface.co/blog/codelion/openevolve

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

#117

Post by rapind »

ainch wrote: post #112

The AI CEOs love to pontificate about AI curing cancer, but it seems like DeepMind is the only one actively working on these research problems, while OpenAI/Anthropic largely chase enterprise/coding revenue.

Google can self fund from their war chest while OpenAI and Anthropic are hat in hand.

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

#118

Post by rapind »

danpalmer wrote: post #108
alecco wrote: post #9

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

Yes. The models are good, the models are fast , and the internal tooling has caught up at this point too. There's a lot of UI/UX/tooling stuff that's still being worked through, integrations with VCS, and solving deeper problems that I probably can't talk about, but I'd say the frustrations of most are about the rate of change much more than the actual abilities. One thing that's interesting is a bunch of internal th…

> a bunch of internal thought leaders who swear by the Flash models over the Pro models

I'm coming around on this too. deepseek-v4-flash is impressive.

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

#119

Post by mrdomino- »

nl wrote: post #109
mrdomino- wrote: post #105

Earlier quoted context omitted.

Tacit knowledge is definitionally not recorded in any of these systems. This proposes to solve the problem of tacit knowledge by getting rid of it. It is not clear to me if that solution is either possible or desirable.

The labs are spending hundreds of millions of dollars hiring people doing many fairly random (but economically valuable) tasks to collect this tacit knowledge for RL. It works really well.

It ceases to become tacit as soon as it is collected.

Maybe this rephrase will help: the proposed solution is to render all knowledge explicit.

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

#120

Post by petra »

charleshn wrote: post #106
Yokohiii wrote: post #62

Earlier quoted context omitted.

This is just a flex post. Be a billion dollar company or get out.

They'll likely make it available at some point, but for now one can use OpenEvolve [0] which is not quite as good but should be a good start to use the same LLM-driven evolutionary framework. [0] https://github.com/algorithmicsuperintelligence/openevolve

There's also: https://github.com/inter-co/science-codeevolve and https://www.turintech.ai/
Post reply on HN