News for hackers. Stuff that matters.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by alecco on Thursday May 07, 2026 @12:02PM (#48051040)
Are Googlers themselves happy using Gemini coding agent instead of Claude Code or Codex? (no snark, I'm really asking)
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by jensensbutton on Thursday May 07, 2026 @12:19PM (#48051237)
Note that coding is not the only use of Gemini or any of these models. It's also not what this article is talking about. Gemini can be not the best coding agent, but very good at other things.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by nine_k on Thursday May 07, 2026 @12:17PM (#48051219)
The point of dogfooding is exactly that: if we're unhappy, we're the ones to improve.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by anthonypasq on Thursday May 07, 2026 @01:26PM (#48052145)
the engineers using gemini have no control over deepmind
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by DeathArrow on Friday May 08, 2026 @01:13AM (#48058841)
Are you in the Gemini team?
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by carbocation on Thursday May 07, 2026 @12:04PM (#48051073)
Last month, Steve Yegge suggested that they are not: https://xcancel.com/Steve_Yegge/status/2043747998740689171
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by NitpickLawyer on Thursday May 07, 2026 @12:19PM (#48051234)
> 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.

a) goog has agentic coding in both antigravity & cli forms. While it is not at the level of cc + opus, it's still decent.

b) goog has their own versions of models trained on internal code

c) goog has claude in vertex, and most definitely can set it up in secure zones (like they can for their clients) so they'd be able to use claude (at cost) within their own projects.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by aleksiy123 on Thursday May 07, 2026 @02:10PM (#48052752)
Agreed, however imo there is def some problems unique to Google which is making the internal experience less than ideal.

Hoping they can figure it out sooner rather than later.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by jatora on Friday May 08, 2026 @08:55AM (#48062382)
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.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by PunchTornado on Thursday May 07, 2026 @12:15PM (#48051205)
This couldn't be further from the truth
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by stormbeard on Thursday May 07, 2026 @12:22PM (#48051274)
Demis Hassabis chimed in on that thread and called it what it is: clickbait.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by typs on Thursday May 07, 2026 @12:34PM (#48051453)
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 a... by beanard on Thursday May 07, 2026 @12:52PM (#48051691)
Sure, but there's cavernous distance between "google = john deere" and "darn I have to use Gemini"
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by FrustratedMonky on Thursday May 07, 2026 @12:50PM (#48051674)
There is value in the "eating your own dog food".

If internal staff aren't happy with the tools they build, typically that should drive improvements to their own tools

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by HardCodedBias on Thursday May 07, 2026 @07:06PM (#48056272)
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 let their devs use Claude/Codex.

This isn’t a security problem, this is a GDM issue with GDM’s promises being far beyond their ability.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by antonvs on Friday May 08, 2026 @08:37AM (#48062184)
> 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 a... by HardCodedBias on Friday May 08, 2026 @11:39AM (#48064686)
I agree with the fact that your company has quota and allocates some to you.

Gemini will conduct seconds to minutes of work before requesting aid. And it will commonly fall over.

Claude/Codex will commonly do minutes to hours of work.

The difference is one to two orders of magnitude. It is immense.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by antonvs on Sunday May 10, 2026 @10:36AM (#48084340)
I look forward to seeing that play out in the market, if true. But from what I've seen, it really isn't.

If you're talking about the ability to churn out low-stakes systems like websites, or variations on existing widely available systems, then perhaps. But once you get to more complex systems, especially large already existing systems, all LLMs today need significant ongoing assistance to prevent them from going off the rails and down rabbit holes. At that point, the advantage you're claiming tends to evaporate.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by PunchTornado on Thursday May 07, 2026 @12:15PM (#48051208)
Codex?
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by j2kun on Thursday May 07, 2026 @12:47PM (#48051627)
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 a... by jatora on Friday May 08, 2026 @08:58AM (#48062416)
Lie? Gemini CLI is unuseable. The IF of gemini models is atrocious. Honestly, how often does your gemini CLI go insane in thought loops and you have to stop it?
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by j2kun on Friday May 08, 2026 @09:11AM (#48062589)
I use Jetski.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by jatora on Friday May 08, 2026 @10:23PM (#48071138)
what does that have to do with gemini coding?
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by dekhn on Thursday May 07, 2026 @12:48PM (#48051654)
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.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by Groxx on Thursday May 07, 2026 @02:22PM (#48052900)
The overall quality of LLM coding tools is shockingly bad. I haven't found a single one without major issues, and many have the same problems reappear every few months, sometimes bad enough to almost break the entire thing (e.g. 100% failure rate in editing files, broken for weeks, with the same cause each time, multiple times in a year).

I'd say I'm surprised by it, but uh

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by DeathArrow on Friday May 08, 2026 @01:13AM (#48058836)
>The overall quality of LLM coding tools is shockingly bad

Most of them were vibecoded in days, so what do you expect? And new versions just add features, they never fix the old cruft.

Probably there would be some money to be made if someone actually takes the time to write a good agent harness.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by stogot on Saturday May 09, 2026 @09:49AM (#48074965)
Which tools were these So I can avoid
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by llmslave on Thursday May 07, 2026 @01:50PM (#48052477)
they use claude code at deepmind
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by robohoe on Thursday May 07, 2026 @02:02PM (#48052642)
Antigravity comes to mind
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by kaueg on Thursday May 07, 2026 @05:37PM (#48055438)
they use a web based vscode like (cider) with a custom agent
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by dzhiurgis on Thursday May 07, 2026 @09:05PM (#48057234)
Not a Googler, but I use gemini in JetBrains Junie and have no issues with it. It's cheap, very fast and most importantly actually listens to you.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by danpalmer on Thursday May 07, 2026 @09:43PM (#48057492)
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 thought leaders who swear by the Flash models over the Pro models. Whether this is true or not doesn't really matter, the interesting bit to me is that we are at a point with the models where "better" models are not necessarily more useful, and that faster with more work on the harnesses may be a better trade-off.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by rapind on Thursday May 07, 2026 @11:20PM (#48058115)
> 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 a... by DeathArrow on Friday May 08, 2026 @01:10AM (#48058818)
>One thing that's interesting is a bunch of internal thought leaders who swear by the Flash models over the Pro models.

I've seen people outside Google favoring flash Gemini models over the Pro.

There are also some benchmarks where flash models have higher scores, so yes, apparently speed does matter.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by gekoxyz on Monday May 11, 2026 @01:26PM (#48097913)
as @goldenarm said just below here, I can't use Gemini Flash for how much it hallucinates. Gemini pro is quite speedy so I am good with using that. On another note, I really like deepseekv4 flash
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by fractorial on Friday May 08, 2026 @01:36AM (#48058989)
You’re absolutely kidding yourself if you genuinely believe that.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by danpalmer on Friday May 08, 2026 @02:25AM (#48059357)
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 a... by fractorial on Friday May 08, 2026 @08:22AM (#48062050)
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 a... by danpalmer on Saturday May 09, 2026 @07:49AM (#48074185)
Google models are well known for being quite terse and efficient on cost – reasonably low pricing for what they are and reasonably low token use for what they achieve.

But as I said do reach out if you are actually a googler, as my points are really about the internal tech which I am pretty positive about.

Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by goldenarm on Friday May 08, 2026 @10:09AM (#48063441)
I'm quite surprised, 3 flash hallucinates way more than 3.1 pro, I stopped using it entirely. Unless you already have 3.2 flash internally :)
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a... by rebeccajae on Friday May 08, 2026 @03:34PM (#48067669)
Most people that I have spoken to that are at Google have complained about the internal Gemini agent and seem to believe it's gotten significantly worse lately. Things like it completely forgetting how to call the tools and eventually giving up having wasted a bunch of time, or the agent completely ignoring code style guidance in an AGENTS.md-esque file.

My experience running Gemma 4 locally has been similar: after maybe one or two tool calls it starts making tool calls however it feels like. Just yesterday, I watched it redefine a tool like read_file(start, end) into read_file(start, number_of_bytes) and it refused to even consider that it was wrong.