Introducing Primus — Transformer Lab
Transformer Lab
Primus is the world’s first fully autonomous AI researcher available to everyone.<br>Sign in nowJoin the WaitlistRead the Docs
primus.lab.cloud
Every innovation we rely on today comes from research: experts read the literature, propose a theory, run the experiments, and publish their findings. This is the research loop, and until now it has always run at human speed where one turn could take months.<br>Katherine Johnson calculating spacecraft trajectories by hand at NASA, 1962.Nikola Tesla in his New York laboratory, c. 1916.
Primus runs the same loop 30× faster. It autonomously hypothesizes, reads millions of papers, codes, runs experiments on real compute, learns and iterates, draws conclusions, delivers artifacts and writes the final paper. The more experiments Primus runs, the better it gets.
We ran Primus for 30 days. It wrote more than 30 complete papers, each on a question never answered before, across LLMs, seismology, physics, crystallography, and biology. Findings that Primus helped produce have already been cited in published research from labs like DeepMind.
How modular is a frontier Mixture-of-Experts?
When RL beats trial-and-error protein design
How DiffusionGemma actually commits tokens
Judging single-image 3D generation without humans
The surprisingly Canadian default values of five AI models
Quantizing Ideogram 4.0 onto a single 3090
A tiny earthquake detector that beats a model 8× its size
How modular is a frontier Mixture-of-Experts?
When RL beats trial-and-error protein design
How DiffusionGemma actually commits tokens
Judging single-image 3D generation without humans
The surprisingly Canadian default values of five AI models
Quantizing Ideogram 4.0 onto a single 3090
A tiny earthquake detector that beats a model 8× its size
←→
→ Read more papers by Primus
What can you ask? Primus isn’t limited to any specific machine learning problem. Ask it to work on anything you would normally request of a team of expert ML researchers. A few examples:<br>Fine-tune a model<br>Fine-tune gpt-oss-120b into a specialist at predicting clinical outcomes from our dataset. It has to run on a single GPU, and I care more about calibration than raw accuracy — benchmark it against the base model and the best closed models.
Write a kernel<br>Our MoE inference is bottlenecked on expert routing. Write a fused Triton kernel for top-k routing on H100s and benchmark it against our current PyTorch implementation.
Extend a research paper<br>Read my paper (arxiv.org/abs/…) and explore the research directions I left open. Pick the most promising one, run the experiments, and write up what you find.
Port a model to a new framework<br>Convert the new Qwen model to work on MLX and do every optimization you can to make it run faster than the original.
Explore a new domain<br>We have ten years of hourly sensor data from our wind farm. Can any modern time-series foundation model beat our physics-based forecast? Find out and write up the results.
Who knows?<br>What comes after the transformer in LLMs? Invent something better and prove it works.
Fine-tune a model<br>Fine-tune gpt-oss-120b into a specialist at predicting clinical outcomes from our dataset. It has to run on a single GPU, and I care more about calibration than raw accuracy — benchmark it against the base model and the best closed models.
Write a kernel<br>Our MoE inference is bottlenecked on expert routing. Write a fused Triton kernel for top-k routing on H100s and benchmark it against our current PyTorch implementation.
Extend a research paper<br>Read my paper (arxiv.org/abs/…) and explore the research directions I left open. Pick the most promising one, run the experiments, and write up what you find.
Port a model to a new framework<br>Convert the new Qwen model to work on MLX and do every optimization you can to make it run faster than the original.
Explore a new domain<br>We have ten years of hourly sensor data from our wind farm. Can any modern time-series foundation model beat our physics-based forecast? Find out and write up the results.
Who knows?<br>What comes after the transformer in LLMs? Invent something better and prove it works.
←→
Primus is officially live.<br>To ensure a seamless experience despite limited GPU capacity, we are gradually onboarding users from our waitlist starting today. Please join the waitlist to secure your spot, and we will grant you access as quickly as we can.<br>If you are an organization looking to bring Primus to your team, please contact us directly.<br>Join the waitlist →
Who is Transformer Lab? We are on a mission to accelerate science by rethinking the entire research journey using AI, and to put that power in the hands of every researcher. We’re starting with machine learning.
Let’s discover the unknown together.