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

131–140 of 159 posts

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

#131

Post by danpalmer »

fractorial wrote: post #126
danpalmer wrote: post #108

Earlier quoted context omitted.

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…

You’re absolutely kidding yourself if you genuinely believe that.

Happy to chat internally if you want, feel free to reach out.

I see a lot of people swearing by one model, but without trying others. I see a lot of opinions based on a snapshot of tooling from ~January, when for example Claude Code was exceptional, but that don't appear to have been updated. In blind tests the models appear to be much closer than some folks would have you believe.

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

#132

Post by byzantinegene »

01100011 wrote: post #124
vonneumannstan wrote: post #40

Earlier quoted context omitted.

>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. A Statement all but guaranteed to look incredibly short sighted by 2030.

The past few years has seen a great rise in casuals reminding us of AIs limitations only to be proven wrong in 6 months. I don't think we're close to AGI, but in 2 years I've gone from AI doubter to AI convert. It's not perfect, but I don't need it to be. The real question to me is if the system can pay for itself. Economics are racing against efficiency gains and it's anyone's guess which wins.

what are those limitations we're talking about? seems most of those the original limitations that people complained about were resolved through workarounds like tools and skills which are more software-engineering than llm advancement.

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

#133

Post by zkmon »

An issue I have been noticing with claude is, for simple tasks, it gives extremely bloated code and artifacts, which sometime does not even work. Gemini balances it quite well, by giving a working solution with the exact amount of code and minimal complexity, that is easier to manage.

The only thing I go to Claude these days, is for front-end code (HTML). Here also, it gives too much of CSS code (60% of the file size), but I'm OK with that as it gives a bit of polished look, though heavy on file size.

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

#135

Post by Yokohiii »

charleshn wrote: post #115
Yokohiii wrote: post #114

Earlier quoted context omitted.

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

Thanks, wasn't really apparent on the github page.

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

#136

Post by HarHarVeryFunny »

Davidzheng wrote: post #125
HarHarVeryFunny wrote: post #72

Earlier quoted context omitted.

There is an apples and oranges difference between AI improving itself (becoming more capable) and AI optimizing software that happens to be used for AI training or inference. A more efficient transformer just costs less to run. "AI improving AI" would be if one generation of AI designed a next-gen AI that was fundamentally more capable (not just faster/cheaper) than itself. A reptilian brain that could autonomously d…

I don't think there is a fundamental divide between implementation speedups and optimization and algorithmic/architecture optimizations

A speedup that changes nothing else is just that: a speedup that changes nothing else.

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

#137

Post by fractorial »

danpalmer wrote: post #131
fractorial wrote: post #126

Earlier quoted context omitted.

You’re absolutely kidding yourself if you genuinely believe that.

Happy to chat internally if you want, feel free to reach out. I see a lot of people swearing by one model, but without trying others. I see a lot of opinions based on a snapshot of tooling from ~January, when for example Claude Code was exceptional, but that don't appear to have been updated. In blind tests the models appear to be much closer than some folks would have you believe.

I’ll admit it swings back and forth on a six month cycle or so; however, cost-to-output matters.

Also, for niche use-cases there are clear winners.

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

#138

Post by antonvs »

exfalso wrote: post #127
risyachka wrote: post #49

Earlier quoted context omitted.

In coding the ambiguity is very, very limited and constrained compared to any non dev job that involves any decision making

That's.. not even close to being the case. It's literally a series of ambiguous questions and strategic decisions. Non-ambiguous is like a first semester algorithms class in university.

There seems to be a category of "coder" which fits the other commenter's description, where someone else makes all the significant decisions and they just write the code. Not coincidentally, that category seems most at risk from AI, because they're basically like a human version of a coding agent.

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

#139

Post by antonvs »

HardCodedBias wrote: post #100
carbocation wrote: post #10

Earlier quoted context omitted.

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

He was entirely correct. He made a follow up after the pushback by GDM. Google’s businesses are very broad and durable. But Google being the only company in the world without access (except for GDM+labs) to a competent coding agent will take a toll. We’ll see how long Google can hold out hoping for GDM to create something that is competitive. I’m guess that within 6 months Google will give up on coding and finally le…

> But Google being the only company in the world without access (except for GDM+labs) to a competent coding agent will take a toll.

I doubt it. I use Gemini CLI daily because Gemini is what work pays for, and I have a personal Claude account. The difference is not that great, especially if you're not doing full vibe-coding. It's unlikely to have the kind of effect you're describing.

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

#140

Post by jatora »

NitpickLawyer wrote: post #17
carbocation wrote: post #10

Earlier quoted context omitted.

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

> He says the problem is that they can't use Claude Code because it's the enemy, and Gemini has never been good enough to capture people's workflows like Claude has, so basically agentic coding just never really took off inside Google. They're all just plodding along, completely oblivious to what's happening out there right now. This is a bunch of gabagoo. Wrong on so many layers, it's not even worth reading further.…

Antigravity's workflow is so slow and buggy with permissions, it is unuseable compared to cc/codex. the only part that is nice is that it allows usage of Opus.

Gemini CLI is an absolute joke. I dont know if its the harness, or the Gemini models' poor instruction following, but more than 50% of my sessions gemini turns insane and ends up in thought loops. In another 25% it does far more updating than I asked or is reasonable.

This is why next to no-one talks about either of them. Does Antigravity's agent manager even work yet without crashing and showing zero conversations? In typical google fashion they released AG and appear to have then set it on autopilot with a skeleton crew of less than 1 developer. Clear issues have not been fixed since day 1. Some settings just do not work. Permissions are not respected.

Post reply on HN