News for hackers. Stuff that matters.
Re:Advancing science and engineering with Antigravity's /tea... by 12347ah on Saturday November 14, 2026 @09:55AM (#50497516)
How to steal scientists' ideas and buckmaster them under the guise of "teamwork".

Also, how to steal C code bases and claim obviously made up performance numbers.

Has professional advertising turned into vibe advertising as well?

Re:Advancing science and engineering with Antigravity's /tea... by gruez on Saturday November 14, 2026 @10:03AM (#50497579)
>How to steal scientists' ideas and buckmaster them under the guise of "teamwork".

That's OpenAI (allegedly), not google

Re:Advancing science and engineering with Antigravity's /tea... by dominotw on Saturday November 14, 2026 @10:03AM (#50497582)
they are all the same
Re:Advancing science and engineering with Antigravity's /tea... by qwerrq on Saturday November 14, 2026 @10:18AM (#50497716)
Doesn't matter with BigTech company we are talking about.

Skype and Hangouts were forbidden for sensitive research at some German universities:

https://www.cms.hu-berlin.de/de/dl/multimedia/bereiche/tele/...

Now everyone leaks everything by using AI even for mundane things like file format conversions.

Re:Advancing science and engineering with Antigravity's /tea... by sobellian on Saturday November 14, 2026 @10:25AM (#50497762)
Mathematicians have reported that OAI models' approach to NS was different from Buckmaster's.
Re:Advancing science and engineering with Antigravity's /tea... by ainch on Saturday November 14, 2026 @12:15PM (#50498711)
Could you share a link or pointer? I tried googling unsuccessfully but would be keen to read more.
Re:Advancing science and engineering with Antigravity's /tea... by sobellian on Saturday November 14, 2026 @02:09PM (#50499830)
There was a scientific american article that went into some detail, see https://tech.yahoo.com/ai/chatgpt/articles/inside-story-behi.... IIUC while they both use forcing to create the blowup the force field was constructed differently. The fine details are beyond me for now.
Re:Advancing science and engineering with Antigravity's /tea... by sidibe on Saturday November 14, 2026 @10:30AM (#50497803)
It's pretty clear "credit" for things is going away, we're going to have to adapt to that. (This includes people achieving big things with or without AI, don't expect anyone to be impressed or care)
Re:Advancing science and engineering with Antigravity's /tea... by customguy on Saturday November 14, 2026 @11:03AM (#50498091)
That's inside that particular singularity, where nothing means anything, you just "adapt".

But from the outside, it's just a bunch of people turning into a blob we don't care about as a whole. We still care about the individual humans who haven't jumped into that gravity well. Humans care about their ancestors, their neighbours, authors and audiences. The people who don't can't fathom that, it's a sort of blind spot for them, but we are completely untouched and unmoved by that. The ideas in your head about the bonds between other people doesn't affect those bonds.

Re:Advancing science and engineering with Antigravity's /tea... by howunfortunate on Saturday November 14, 2026 @11:43AM (#50498405)
That has been true of a lot of good science for a while.

The person who gets the credit is just the person who wrote the grant. They are usually _capable_ of doing good science but the demands of being a PI mean they are mostly just grant writers and administrators. Huge teams of unknown postdocs, grad students etc. are doing most of the work.

Re:Advancing science and engineering with Antigravity's /tea... by taylorbc1103 on Saturday November 14, 2026 @10:12AM (#50497659)
Interesting
Re:Advancing science and engineering with Antigravity's /tea... by shmageggy on Saturday November 14, 2026 @10:21AM (#50497740)
I think the authors also used Antigravity to write this article, because it sucks at communicating whatever point it’s trying to make. I think it’s something like “We did the OpenAI 100 problems thing, but across many disciplines, and in collaboration with the experts instead of just dumping results on the world, and we also made the tooling feature available,” but I’m not sure because it has that distinct Gemini flavor of packing in so many low-level details that the actual point becomes entirely obscured.
Re:Advancing science and engineering with Antigravity's /tea... by 5555watch on Saturday November 14, 2026 @10:30AM (#50497801)
It seems like they already announced /teamwork earlier [0], but now just announced that they got some scientific results out of it. They probably intentionally want to keep this low key, but in that case it's not clear why announce it at all.

[0]: https://antigravity.google/blog/teamwork-when-ai-becomes-a-r...

Re:Advancing science and engineering with Antigravity's /tea... by Jeff_Brown on Saturday November 14, 2026 @10:33AM (#50497824)
It sounds like they're saying they now offer an option, "/teamwork", that will throw more computer at a problem by choosing a team and a workflow that you the user don't have to (or get to?) know about.
Re:Advancing science and engineering with Antigravity's /tea... by verdverm on Saturday November 14, 2026 @11:40AM (#50498382)
> I think the authors also used Antigravity to write this article, because it sucks at communicating whatever point it’s trying to make.

The pattern seems to be pervasive at Google. Too much Ai, not enough human, top-down orders

Re:Advancing science and engineering with Antigravity's /tea... by gradus_ad on Saturday November 14, 2026 @12:03PM (#50498588)
It is a shame that Gemini prose has become too detail dense in recent releases. Its prose was one of its distinct advantages over Claude with that annoying Claude speak...
Re:Advancing science and engineering with Antigravity's /tea... by lern_too_spel on Saturday November 14, 2026 @04:02PM (#50500772)
I'm pretty sure they didn't because of the following nonsensical sentence and how generally disorganized the post was:

"In under eight days, the engine gained roughly 2,600 Elo, reaching 1,885 Elo, placing it between KataGo at 16 and 32 visits per move."

Re:Advancing science and engineering with Antigravity's /tea... by slopinthebag on Sunday November 15, 2026 @05:58AM (#50505942)
it started at -715 elo obviously
Re:Advancing science and engineering with Antigravity's /tea... by avodonosov on Saturday November 14, 2026 @04:11PM (#50500864)
Not just overly detailed, it misses important hints that would help the reader and puts several things into one sentence in a way that the sentence is difficult to follow:

> For n-bit integer multiplication, multi-agent campaigns simplified the theoretical Turing-machine bound below n log n, while a separate effort gave a new O(n log n) algorithm on a single two-dimensional grid whose C implementation matches the GNU Multiple Precision Arithmetic Library (GMP) bit-for-bit up to a billion bits.

Is "simplify a bound" a normal wording? What does it mean to simplify a bound?

Re:Advancing science and engineering with Antigravity's /tea... by anematode on Sunday November 15, 2026 @12:39AM (#50504313)
Wow, that passage is garbage. This "bit-for-bit" stuff is the newest LLMism, by the way ...
Re:Advancing science and engineering with Antigravity's /tea... by classified on Saturday November 14, 2026 @11:17AM (#50498207)
Sloppification is now called "advancing". That may even be innovative.
Re:Advancing science and engineering with Antigravity's /tea... by dava96 on Saturday November 14, 2026 @11:31AM (#50498319)
Interesting that a Rust re-write pre optimisation was 30% slower than the C++ equivalent.

I wonder if they optimised the C++ it would actually have more speed benefits than the Rust alternative. Only they can't claim it's a Rust rewrite like every other company at the moment.

Re:Advancing science and engineering with Antigravity's /tea... by avodonosov on Saturday November 14, 2026 @04:19PM (#50500930)
I also thought of what speedup the tool could make for the C++ original
Re:Advancing science and engineering with Antigravity's /tea... by gdevenyi on Saturday November 14, 2026 @12:30PM (#50498886)
This doesn't tell me how to use it.
Re:Advancing science and engineering with Antigravity's /tea... by mirrokni on Saturday November 14, 2026 @12:41PM (#50499007)
As noted by others, we already announced parts of /teamwork in Antigravity here: https://antigravity.google/blog/teamwork-when-ai-becomes-a-r... with more visualizations and more. Thi post was meant to report some advances in math/science/coding/engineering to show-case examples of tasks you can do with it.

We are constantly improving/evolving /teamwork and pushing those changes for external users. Will also post more about improvements and details for building teams of agents dynamically as Antigravity blog posts soon. Stay tuned!

Also I added a list of examples here: https://x.com/mirrokni/status/2121351383236436247?a=ma9UPZg_... and https://lnkd.in/p/esVTpR6p. I'll add a comment with examples as well.

Re:Advancing science and engineering with Antigravity's /tea... by mirrokni on Saturday November 14, 2026 @12:46PM (#50499055)
Here is a short list of example results reported on the post; again we will have dedicated Antigravity posts for some of these.

* Math Open Problems & Formal Verification: Reporting 10+ open math and CS theory problems solved including 50M-line Lean 4 proof of Courtade–Kumar conjecture plus progress on several open problems in quantum query complexity, Tarjan's Deque Conjecture.

  Also autonomous Lean formalizations of the Weil (1.8M lines), Birkhoff, and 3D Bochner–Riesz conjectures via Teamwork-LEAP, plus updates on Deep Review for STOC’27.
* Chemistry & Discovery: 95% top-1 exact match on NMR molecular structure elucidation (nearly 2× single-agent). Also empowering Nuclear Fusion and Quantum algorithm results as well autonomously generating a CausalAnalyst Benchmark. In addition, we show how /teamwork can start from Alphazero paper, implement a competitive go game, and autonomously improving it by playing with KataGo to get to the medium Elo level.

* Several Systems, TPU Kernel, & Infra: * Clustering 1-Trillion-edge graphs on FarArray and RDMA (up to 180× faster), * 800K-line Zircon & 170K-line libgav1 safe Rust rewrites (20–30% faster than C++/ASM), * 4.09× JAXBench TPU kernel speedups with DuoDiscover, * Google internal examples: surpassing 1 PiB fleet memory savings, and 24% fewer Borg TPU preemptions for Borg Scheduling.

Re:Advancing science and engineering with Antigravity's /tea... by esafak on Saturday November 14, 2026 @01:11PM (#50499297)
Is CausalAnalyst the causal inference benchmark it talks about? Where are the results? This is a poor blog post.
Re:Advancing science and engineering with Antigravity's /tea... by wslh on Saturday November 14, 2026 @01:18PM (#50499358)
FWIW, since Argon 4 was launched I used Antigravity (without the /boost or the /teamwork flags) for "playground research" and had some discoveries in cryptography[1] and speeding up Python, removing the GIL, improving the JIT, and optimizing it for certain libraries (e.g. NetworkX) [2]. I don't know how stable is the Python one but it passes the included tests. I have spent some GC budget on it though.

[1] https://arxiv.org/abs/2611.00512

[2] https://github.com/srw/cpython-experimental

Re:Advancing science and engineering with Antigravity's /tea... by doctorpangloss on Saturday November 14, 2026 @09:25PM (#50503375)
I think if you just keep focusing on ridiculously generous usage limits compared to Anthropic in order to harvest the use cases of the 99 percent, like making shitty websites, but which benefits people like me, you will find success.
Re:Advancing science and engineering with Antigravity's /tea... by drivebyhooting on Saturday November 14, 2026 @01:43PM (#50499606)
When to use teamwork vs boost vs swarm?

Both take a long time. It used to be that antigravity was much faster than codex, but with recent releases it is substantially slower.

Inspecting the agents communication in teamwork, there seems to be an overwhelming amount of ceremony: BRIEF.md, specialized roles, multiple rounds of checking. Is all that necessary? Codex also uses agent “swarms” but unless they’ve hidden how the sausage is made, it doesn’t seem so heavyweight.

Re:Advancing science and engineering with Antigravity's /tea... by dleslie on Saturday November 14, 2026 @06:03PM (#50501958)
Can you please let the product team know that there's space between Pro and Ultra pricing?

I can't afford/allow for ultra pricing for personal projects, but Pro runs through in about two days of casual usage for me. I've paid for extra credits, but my god are those not worth the price.

I would love to pay for a sub that's between Pro and Ultra.

Re:Advancing science and engineering with Antigravity's /tea... by bionhoward on Saturday November 14, 2026 @06:52PM (#50502342)
Neither one has privacy so it’s pretty much just a toy or for open source folks whose codebases get stolen by Google either way
Re:Advancing science and engineering with Antigravity's /tea... by r_lee on Sunday November 15, 2026 @07:05AM (#50506322)
is this actually true? there's no way to turn it off?

why would anyone use Google then? gotta pay for your IP to get stolen? lol

Re:Advancing science and engineering with Antigravity's /tea... by 05 on Saturday November 14, 2026 @07:07PM (#50502445)
Second pro sub is the usual middle ground, same as with other providers. You can switch to second account using an alias (agy2='unshare ... exec agy' to remap $HOME/.gemini to e.g. .gemini2).

Although using another provider for the secon sub is probably a better idea since having a different model doing review would uncover more issues than asking the same model that generated the code..

Re:Advancing science and engineering with Antigravity's /tea... by stbenjam on Saturday November 14, 2026 @12:52PM (#50499120)
It is not clear to me how or if /teamwork is any different than Claude dynamic workflows.

Antigravity as a harness feels very behind. There's not even any auto mode. And they announced /goal long after I ever felt the need to use it in CC or Codex.

Re:Advancing science and engineering with Antigravity's /tea... by p_l on Saturday November 14, 2026 @01:32PM (#50499486)
Auto mode has been there for few versions, and recently (1-2 days ago?) became the default
Re:Advancing science and engineering with Antigravity's /tea... by nmfisher on Sunday November 15, 2026 @02:54AM (#50504953)
It's there, but it still doesn't actually work for me, I need to approve almost everything.
Re:Advancing science and engineering with Antigravity's /tea... by p_l on Sunday November 15, 2026 @03:57AM (#50505226)
Interesting, I will have to review my settings because I did mess around a lot with it before Auto mode
Re:Advancing science and engineering with Antigravity's /tea... by CamperBob2 on Saturday November 14, 2026 @02:19PM (#50499912)
There is (--mode auto), but you can't access it without restarting the harness. Even then, you'll get plenty of mother-may-I showstoppers. I had to resort to using the --dangerously-skip-permissions option to get anything done. The good news is that Carbon is a pretty awesome model once you do get it working.

Seems likely that the people who maintain Antigravity don't use Antigravity to do it. It has too many rough edges that would be trivial to fix if someone actually noticed them.

Re:Advancing science and engineering with Antigravity's /tea... by p_l on Saturday November 14, 2026 @03:26PM (#50500479)
I read changelog every release, and there's always a lot of work updating auto mode in last series (1.5.x)
Re:Advancing science and engineering with Antigravity's /tea... by s_u_d_o on Saturday November 14, 2026 @01:05PM (#50499232)
The amount of breakthroughs this could deliver. Previously we should’ve established R&D departments, prepare multi-cultural teams, all to work on a single project. Today? I can see a domain expert, guiding antigravity and delivering fast.
Re:Advancing science and engineering with Antigravity's /tea... by owebmaster on Sunday November 15, 2026 @05:05AM (#50505601)
even Google can't deliver antigravity with an acceptable quality. Google developers behind it are supposed to be domain experts and they are not delivering fast. Time to wake up
Re:Advancing science and engineering with Antigravity's /tea... by nightski on Saturday November 14, 2026 @01:17PM (#50499348)
The labs really want to make it seem like they are all about openness, research, supporting science and advancing humanity. To some extent they have contributed to those areas. That said, it's not aligned at all with their business. Their business is not any of those things. Makes you wonder why they just aren't honest about their goals and objectives.
Re:Advancing science and engineering with Antigravity's /tea... by kats on Saturday November 14, 2026 @01:29PM (#50499471)
Google is missing LLMs the way that Microsoft and Intel missed cell phones.
Re:Advancing science and engineering with Antigravity's /tea... by riddlemethat on Saturday November 14, 2026 @02:50PM (#50500156)
I’m not sure if they are that far behind given the integration forced into every single one of their consumer products but yeah their developer LLM focus has been very disappointing.

I still don’t understand why they don’t use their massive market position to give more value to Google workspace customers to have more access to their models for teasing higher value plans. The existing credits timeout before they even build a playwright scraper.

Re:Advancing science and engineering with Antigravity's /tea... by owebmaster on Sunday November 15, 2026 @05:07AM (#50505614)
> given the integration forced into every single one of their consumer products

Sounds like bing integration to Windows to me

Re:Advancing science and engineering with Antigravity's /tea... by CharlieDigital on Saturday November 14, 2026 @01:36PM (#50499524)
Related: I've been finding a lot of success (defined as more autonomy with less quality dropoff) with team-based workflows.

A lot of evidence for this.

- Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams (https://arxiv.org/abs/2606.01770) talks about multi-agent, role-based adaptive harnesses collaborating on non-homogeneous workstreams

- team-solve (https://github.com/guregodevo/memdoor/tree/main/examples/wor...) team of small models beats Fable on LiveCodeBench

- Agensh paper (https://arxiv.org/html/2609.26781v1) also talks about "role-playing agents to study autonomous cooperation"

All show that role-based, multi-agent setups improve performance.

Re:Advancing science and engineering with Antigravity's /tea... by jdw64 on Saturday November 14, 2026 @08:21PM (#50503005)
I'm not really sure. I've tried the EGM plugin too, but the issue that “the auditor verified it” doesn't solve the auditor's own reliability problem and just circulates the responsibility for verification within one layer—honestly, I'm curious how they solve that. What I want to know is this kind of thing.

In practice, when I use the Antigravity Argon multi-agent model, the problem of auditors making false completion reports still exists. I wish the Antigravity team would write something like a whitepaper on how they actually use the Gemini models. It works properly in other models' harnesses, and I pay for credits and use Gemini, but I've never gotten results that good from Gemini.

Re:Advancing science and engineering with Antigravity's /tea... by mtzaldo on Saturday November 14, 2026 @09:41PM (#50503464)
My experience using oh-my-claudecode as orchestrator and using the teams options was a mix. For one side the work completed was very good and it took less time. The main issue I had was my hard drive was getting full because I was using worktrees and the weekly tokens were spent in about 2 days (plan Max 20x)because all the context was being duplicated in all the agents as part of the teams. Not sure how Antigravity works, but I hope it doesn't have the context issue.
Re:Advancing science and engineering with Antigravity's /tea... by aaabbbccccc on Sunday November 15, 2026 @05:15AM (#50505665)
Google is a mess. I have been doing essentially slave labor for 8 months for instance several high severity bugs I have submitted to Google have been patched in not one but three firmware updates yet they still have not paid me, you can read about it here www.github.com/jegly/jegly
Re:Advancing science and engineering with Antigravity's /tea... by stoltzmann on Sunday November 15, 2026 @05:42AM (#50505833)
>slave labor

lol nobody is forcing you to work for free

Re:Advancing science and engineering with Antigravity's /tea... by embedding-shape on Sunday November 15, 2026 @07:36AM (#50506493)
> I've carried out independent security research for a number of vendors and OEMs

> I have been doing essentially slave labor for 8 months

Please understand what you're doing, "slave labor" isn't what you've put yourself through.