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.
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, you just have to feel good about what you did being used.
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.
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.
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.
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.
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.
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...
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?
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.
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!
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.
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.
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..
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.
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.
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.
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
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.
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.
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
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.
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.
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
46 comments
[ 0.23 ms ] story [ 40.6 ms ] threadAlso, how to steal C code bases and claim obviously made up performance numbers.
Has professional advertising turned into vibe advertising as well?
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.
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.
[0]: https://antigravity.google/blog/teamwork-when-ai-becomes-a-r...
The pattern seems to be pervasive at Google. Too much Ai, not enough human, top-down orders
"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."
> 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?
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.
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.
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.
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.
why would anyone use Google then? gotta pay for your IP to get stolen? lol
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..
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.
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.
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.
Sounds like bing integration to Windows to me
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.
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.
lol nobody is forcing you to work for free
> 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.