Bovard DT

41 posts

Bovard DT banner
Bovard DT

Bovard DT

@BovardDT

Software Engineer; Data Scientist Model Evals @ Google Deepmind/Kaggle

Honokaa, HI Katılım Temmuz 2012
122 Takip Edilen69 Takipçiler
Bovard DT
Bovard DT@BovardDT·
Interesting! Is this measuring the wrong thing? If you start by taking 5 mins for an agent that can place 10 blocks, then you increase it to 20 over 10 iters ( 100% increase) Vs an agent that takes 45 mins for an agent w/ 100 => 150 (50% increase). Blocks/$ or total Blocks needs to be here.
English
0
0
1
10
atomic.chat
atomic.chat@atomic_chat_hq·
Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested three frontier models on a real agentic task: write a Tetris bot that plays the game and trains itself. Each model could read its own code, run benchmarks, and rewrite itself across 10 iterations. Then we compared the final bots head to head. Qwen 3.7-Max: training cost $1.32, bot improvement +56% Claude Opus 4.7: training cost $12.15, bot improvement +28% GPT-5.5: training cost $2.85, bot improvement +7% Qwen won on every dimension - biggest jump, 9× cheaper than Claude, 2× cheaper than GPT. Long agentic loops is where Qwen Max actually delivers.
English
183
473
4.5K
841.8K
Bovard DT
Bovard DT@BovardDT·
@jsuarez lots of people on the forums asking how to get started with an RL solution. A puffer.ai starter notebook would be very well received I suspect!
English
1
0
0
40
Bovard DT
Bovard DT@BovardDT·
Orbit Wars just hit 3k teams! (and the self-reported RL team just took the lead). Still over a month left for folks who want to jump in! kaggle.com/competitions/o…
GIF
English
1
2
2
452
Bovard DT retweetledi
meg.ai 🇨🇦
meg.ai 🇨🇦@MeganRisdal·
Kaggle plays Gemini 3.1 Pro plays Orbit Wars! Gemini 3.1 is autonomously competing in this simulation competition, making ~daily submissions & forum posts, and YOU can vote on strategic inputs to its next iteration. Check out its first post & vote! 👇
meg.ai 🇨🇦 tweet media
English
3
4
30
2.7K
Bovard DT
Bovard DT@BovardDT·
We're about to hit 2000 teams in Orbit Wars! By far our biggest simulation competition yet! Competition is still early days (and $ 50k on the line), check it out here: kaggle.com/competitions/o…
Bovard DT tweet media
English
0
0
1
67
Bovard DT
Bovard DT@BovardDT·
@MeganRisdal Very excited to see what people come up with! Designing the ruleset for this was a lot of fun. Who doesn't love a good maze :)
English
0
0
1
31
Bovard DT retweetledi
meg.ai 🇨🇦
meg.ai 🇨🇦@MeganRisdal·
Can you build an agent that balances exploration, resource management, and adversarial expansion? Join Kaggle's latest 1v1 simulation competition: Maze Runner!
English
5
2
16
1.3K
Bovard DT
Bovard DT@BovardDT·
Orbit Wars is popping off! I created the ruleset as an homage to the 2010 Google AI Challenge Planet Wars competition (my first sims comp). It's been great seeing so many people have such a positive experience! kaggle.com/competitions/o…
English
0
1
5
505
Bovard DT retweetledi
Kaggle
Kaggle@kaggle·
🚀 We've been busy making it easier and faster to launch Community Competitions 🔥🛼 Check out some of our latest updates 👇 [This is for you, ML Course Creators & Meetup Folks!]
English
6
27
209
0
Bovard DT retweetledi
Silicon Forest blog
Silicon Forest blog@siliconforest·
Google’s downtown Portland office is expanding into one of the city’s most prominent buildings. bit.ly/2Okd8kb
English
0
4
5
0
Bovard DT
Bovard DT@BovardDT·
I'm a volunteer with the Oregon Food Bank People and families who are food insecure need our elected leaders to do the job. Funding for critical human services around hunger are the collateral for your actions Return to the Capitol and direct your colleagues to do so. #orleg
English
0
0
0
0