Lisette (she/her) retweeted
🚀Tomorrow: IrisGo for Solopreneurs launches on @ProductHunt.
Show it a task once. @irisgoai handles it from there 🤓
Get notified when we go live: producthunt.com/products/iri…
For years, CUDA engineers wrote kernels by hand and tested them one at a time. But now, AI now handles much of that work, and engineers increasingly direct it.
At INT21, we are taking this shift even further, moving from single kernels to complete inference engines. This week, we had 2 engineers direct AI to build 20 engines in just 2 weeks. We achieved faster text generation on all six language models tested (up to 2.4× faster than SGLang), while our audio generation performs up to 7.5× faster than vLLM.
Our founder and CEO spoke to @BusinessInsider Insider about how CUDA talent has always been scarce, and AI is now closing that gap. Read more: businessinsider.com/cuda-eng…
When LLMs can solve frontier math, why do we still need Autograd with tons of historical legacy? Just throw it away. We made another concrete step in system software generation.
What if self-improving agent swarms could build and own training infrastructure? SwarmOS, our cloud-native platform for running specialized agents, which is backed by GPT-6 Astra, generated a Rust/CUDA fully sharded data-parallel trainer for Qwen3.8-27B.
The results: 11.5× higher throughput than eager PyTorch FSDP2, and 21.5% higher than tuned PyTorch on the same eight NVIDIA B200 GPUs.
We're building this training infrastructure at INT21, where agent swarms develop, validate, and continuously improve specialized systems end-to-end. A trainer that owns one model, one objective, one hardware configuration gets significantly more out of the compute you already own.
Read more in our latest post: int21.ai/insights/swarmos-gp…
CUDA's moat isn't disappearing—it's shifting.
As coding agents scale code generation, verification becomes the bottleneck. The infrastructure that validates, optimizes, and self-improves at production scale wins.
New game. New moat. Read more in Business Insider, where our @bingxu_ shares his thoughts: businessinsider.com/nvidia-c…
We’re starting to roll out beta access to the @int21_ai PTX Kernel Factory. Because spot GPU availability is limited, access will expand gradually.
I only know how to program vector add, but self-improvement has enabled our infra to learn PTX programming. This is how world-class GPU programming expertise can become scalable.
Everyone is talking about self-improving AI. Almost all of that conversation is about models improving themselves, a path that will take years and billions of dollars.
We took a different path.
Check out our definition of a new category: Self-Improving Compute Infrastructure, where AI agent swarms continuously improve the software that AI runs on.
Why infrastructure first? Because it is measurable now. And we chose the hardest proving ground on purpose: GPU kernels, where you cannot fake a result. Every candidate has to prove it works before it gets timed, and the timing happens on real hardware.
The full post covers what the category is, why kernels came first, and what changes for teams, costs, and hardware when infrastructure improves itself. int21.ai/insights/what-is-se…
Meta released Muse Spark 1.1 this week. We tested it inside SwarmOS, our platform for coordinating large population of agents, and gave it an ambiguous market question: is Huawei's optical telecommunications capability a risk factor for Lumentum and Marvell inside data center networking?
Three model configurations ran the same question:
⚙️ GPT-5.6-Sol-max: 44 agents, 581M tokens, about five hours
⚙️ GPT-5.6-Terra-xhigh: 17 agents, 36M tokens, about one hour
⚙️ Muse Spark 1.1-xhigh: 29 agents, 40.5M tokens, about 30 minutes
All three reached the same bounded conclusion.
Takeaways:
→ Treat the control plane as the durable asset. Models will change faster than enterprise systems. The strategic choice is not one permanent model; it is a governed portfolio behind stable interfaces.
→ Route models by role. The fastest worker, the best evidence reviewer, and the most conservative synthesizer may be different models. Swarm architecture makes that a routing decision instead of an all-or-nothing vendor decision.
→ Measure cost per trusted result. Token price is only one input. A cheaper run that requires extensive verification can be more expensive in production.
→ Test operational semantics, not just model quality. A strong model can still fail if those contracts are ambiguous.
The larger signal: Muse Spark 1.1 crossed a more useful threshold than a benchmark win: after rapid adaptation by the harness, it became a productive worker and delivered a large-scale result in about 30 minutes. The winning system isn't one model, it's a control plane that keeps recruiting, testing, and replacing models as capabilities and costs change.
Full breakdown, plus links to all 3 research reports: int21.ai/insights/muse-spark…
Stop Waiting for a Bigger Context Window
(post from our CEO/founder: int21.ai/insights/stop-waiti…)
At INT21, we are all-in on self-improving multi-agent systems. We have built SwarmOS, our cloud-native platform for running specialized agents, and our first product, PTX Kernel Factory.
The biggest change is not simply a larger context window. It is what frontier models make possible when they are orchestrated: turning one enormous context problem into a coordinated team of smaller, evidence-seeking tasks.
About a year ago, I was exploring how AI agents could generate CUTLASS C++ kernels, NVIDIA’s building blocks for high-performance GPU computation. By my count, the entire CUTLASS codebase represented roughly five million tokens. At the time, the best production model available to us offered a one-million-token context window.
The central blocker was never code generation. It was finding and preserving the right evidence across the repository.
Rather than wait for a magical five- or ten-million-token model, I ran the one-million-token model several times in parallel. Each agent studied a different portion of the codebase, and combined their findings as the final step.
It was a simple architecture, but it established the principle behind our work today:
When context stops fitting vertically, scale it horizontally.
A Bigger Window Is Not Better Context
Even when millions of tokens technically fit inside a model, the model must still separate signal from noise. A bigger window introduces more irrelevant information, more intermediate output, and more competition for attention.
Multi-agent systems address this structurally. Specialized agents explore different parts of a codebase, investigate the same question from independent angles, and return distilled findings to a coordinating agent. When a subproblem is still too large, it gets divided again.
The goal is not infinite context. It is effective context.
A General Solution for Complex Problems
At INT21, we use SwarmOS not only for hard engineering problems, such as expert-level PTX generation, but also to understand complex business landscapes.
To test this outside a codebase, we pointed SwarmOS at a different kind of long-context problem:
Research question
Could Huawei, CXMT, and China's AI stack create pressure on Western AI compute economics?
The research ran autonomously using public information. The system involved 27 agents, performed 166 web searches, visited more than 200 web pages across 73 unique domains, and ran for about two hours.
In total, it consumed 119 million tokens.
We are sharing the report in this article because we believe this is a topic many people will want to understand more deeply. But the report is also a demonstration of the broader point: multi-agent orchestration is the real long-context breakthrough.
Long Context Is Becoming a Systems Problem
So, are the latest AI generations solving long contexts?
Not by making context infinite, but in an agentic way.
It is helping solve long context by making it divisible, searchable, and composable.
That is why INT21 is all-in on multi-agent systems. At INT21, we are building Self-Improving Compute Infrastructure, and SwarmOS is the operating system behind a massive number of agents.
PTX Kernel Factory is now in beta for teams working on GPU kernel generation and AI compute infrastructure. Accepted participants receive limited-time free access and $100 in credits. Join the beta: int21.ai/products/ptx-kernel…
Bigger context windows do not solve long context. Orchestration does. Our SwarmOS ran 27 agents through 119M tokens of research in 2 hours, autonomously. Check out our full research here: int21.ai/insights/stop-waiti…
The same architecture powers PTX Kernel Factory, which is now in beta. Accepted participants receive limited-time free access and $100 in credits: int21.ai/join-beta?product=p…
Lisette (she/her) retweeted
🌅 @AI_in_the_AM is LIVE in 30 minutes:
9:30am PT: @bingxu_ of @int21_ai – agent swarms improve GPU kernels to get the most from compute infra
10am PT: @bakkermichiel, co-author of Europe 2031 – what happens if Europe fails to wake up to AI
teapaw.org/i/broadcasts/1rGmqqRMW…
Lisette (she/her) retweeted
9am today on the stream! Join Us! teapaw.org/i/broadcasts/1kKzDDVRp…
I started INT21 two months ago, and I’m proud to announce that we’re coming out of stealth today with our first product: PTX Kernel Factory. We’ve created the first self-improving agent swarm for producing expert-level PTX kernels autonomously and at massive scale. int21.ai
Replying to @irisgoai @TechCrunch
Lovely read, its great that Watch and Learn made a good impression! 👇⏬
techcrunch.com/2026/05/20/ir…
Lisette (she/her) retweeted
Some personal news: later this month, I'm moving to NYC to join the tech coverage team at @Inc! My focus will be the same powerhouse industries I covered for the L.A. Times in recent years: AI and social media.
Send me your tips, your source ideas, your bagel recs!
News: @_B_Contreras_ is joining Inc. as a staff reporter, where he will be covering AI, creators and social media, and tech startups. He comes to us from the Los Angeles Times where he was the Times' first-ever artificial intelligence beat reporter.
Prior to that, he wrote about the future of entertainment and social media. His piece “How Instagram and TikTok prey on pregnant women's worst fears" took second place at the Southern California Journalism Awards. His reporting work has also appeared in the Seattle Times and San Antonio Express-News. Contreras will be based in our New York headquarters and will start May 29.
Have an idea for an innovative idea or company he should cover? Drop it in the comments below.
Lisette (she/her) retweeted
Want to interview businesses and public sector organisations worldwide with innovative approaches to training/"upskilling" employees in hot skills.
I need 3 case studies in Europe/Americas/Asia/Africa. For Financial Times. Email me: [email protected] #journorequest
Impressed that a person that worked at Facebook 9 years ago and was fired after 9 months got a news story today about his experience businessinsider.com/ex-faceb…
1
44

















