Brooklyn, NY
Joined December 2010
- Tweets414
- Following688
- Followers922
- Likes5.9K
Ryan Holbrook retweeted
📣 If you have opinions about chart crimes and plotslop, we have an arena for you. Go vote for the best models on Chart Arena, live on Kaggle now! kaggle.com/benchmarks/kaggle…
ALT A screenshot of Chart Arena on Kaggle showing plots created from prompts+data for side-by-side voting.
Ryan Holbrook retweeted
Interesting write ups are being published now that the competition is closed
Many are are inference engineering
I want to make all these tricks available to future agents who are experimenting in the same domain
How do we contribute this to public knowledge town square?
Ryan Holbrook retweeted
How do competitors with restricted compute find opportunities to win, build their careers, and earn medals?
Last year, Isaiah Pressman finished 2nd in a competition on his home PC, behind a team running 8 H100s. This year, he won on a cluster.
In the first episode of Beyond the Leaderboard, three Orbit Wars competitors weigh scale against clever engineering.
Here’s a sneak peek:
A cool new Kaggle competition with a new submission format. Instead of submitting a CSV of predictions or an inference script, you'll submit a Gemma 4 agent you design yourself together with LoRA adapters to finetinue its performance on coding tasks.
Post-train an open model into a coding agent that accelerates developer workflows on everyday hardware.
The Gemma 4 Developer Agent Competition, hosted by @googlegemma and Kaggle, is live!
💰 Total Prize Pool: $100,000
⏰ Entry Deadline: November 25, 2026
Ryan Holbrook retweeted
As a test of our progress to advance the frontier of AI research, in June we entered the next generation of our autonomous AI research system, AIRA₃, in a live Kaggle competition run by NVIDIA to fine-tune a 30B Nemotron model. The challenge was to teach the model to reason better — all competitors had access to the same information and were graded externally on a private test set.
AIRA₃ placed 8th out of ~4,000 teams to win Gold, outperforming human competitors who had access to the same frontier tools.
We believe this is a reliable signal that AIRA₃ can improve a targeted capability of an AI model at a level similar to human experts.
Ryan Holbrook retweeted
We (@JamilCSemaan , @kagglingdieter, and me) published a blog on the @kaggle Nemotron Challenge top solutions! Lots of great work happened in this competition
developer.nvidia.com/blog/le…
Ryan Holbrook retweeted
🏆 New @kaggle competition! 🏆 Autonomous Agent Prediction: submit an agent to autonomously solve multiple unseen ML tasks from a common distribution.
It's a test of where we're heading -- building & evaluating agents that continually learn, generalizing across novel but related tasks within token budget constraints.
kaggle.com/competitions/auto…
Ryan Holbrook retweeted
Deep Past Challenge was my first kaggle competition without coding, and with @raja_biswas we came 3rd 🥉
It was fun to use agentic tools to learn about life and settling disputes 4000 years ago. Thanks @kaggle for hosting
👇10 minas of silver (~5 kg) — enough to buy a house.
Ryan Holbrook retweeted
NVIDIA is hosting a Kaggle competition. How can you train a nemotron nano model to solve scientific questions?
I hope you'll enjoy it! For this competition @kaggle secured NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs from Google Cloud. These GPUs are much more powerful than the usual Kaggle GPUs. Come and try these beasts!
kaggle.com/competitions/nvid…
Would make a great Kaggle competition, too. Reach out if you're interested in seeing something up
Open call for AI evals to accelerate the creation of connectomes for larger/more complex brains; Adam is one of the people I trust the most on this issue and believes today’s agents can help with connectome proofreading, currently a labor-intensive process.
4
223
Ryan Holbrook retweeted
1/ Today the biggest score jump in AIMO history happened: we sit at 38/50.
Usually score increases are on the order of few points, and it is unusual for the distance to the other competitors to be this big, especially as most of easy problems have now been solved.
Ryan Holbrook retweeted
Shocking results: From 0/50 to 23/50 IMO-level problems in a day!
Taking into account that these are very hard problems and your model has on average just 6 minutes of H100-time per problem, this is quite an achievement.
We just launched the latest installment of AIMO. Proud to be a part of this great competition series. Try it out and help advance the SOTA for open math models.
Competition Launch Alert! AI Mathematical Olympiad hosted by @AIMOprize.
🎯 Create open-source algorithms and models that can solve olympiad-level math problems written in LaTeX format
💰 $2M+ Prize Pool
⏰ Entry Deadline: April 8, 2026
kaggle.com/competitions/ai-m…
Ryan Holbrook retweeted
AIMO3 has launched! Check out our mini-benchmark of reference problems below & help us shrink the gap to commercial LLMs to zero!
Ryan Holbrook retweeted
110 problems created by an international team
❌ Not scraped from the internet
❌ Not in any training dataset
❌ Not seen by any model before
This is how you test TRUE reasoning ability.
Can your model actually SOLVE problems?
Or just pattern spot?
AIMO3 will tell you 🔍
Ryan Holbrook retweeted
Our OpenAI x AIMO that we made in March 2025 revealed on an unprecedented scale the difference between the math reasoning performance of open-source vs closed-source LLMs.
Join us for AIMO3 to shrink this gap to zero!
