Tyler Marques

Awesome to see @EGafni & Diogo launch their first model Jev! Verification is the bottleneck for building great AI learning environments. Jev is a welcome, unique, addition to our toolkit @goodstartlabs Typed decisions, probabilities for each option, free output tokens! On our sample: • Jev agreed with Fable 5.1 nine times out of ten • ~200× lower grading cost • <0.5 seconds per grading call That means more eyes on what agents are doing and what we’re teaching them. More on how we’re using it to build game environments, experts to play them, and ensuring they teach the right things: goodstartlabs.com/research/v…

we get asked a lot, why AI & games? I love games Some test strategy, others humor, speed, trust. Simple rules lead to the craziest situations. There's nowhere to hide, will you win or lose? To win any game you need to be right, often. AI is entering its rebellious teen era It's now extremely capable, but lacking: Judgement 〜 to wield that power responsibly Wisdom 〜 to know when it's mistaken Trust 〜 built through reliability and understanding Games will help us measure and improve those capabilities. They'll put what AI can do on display; in a human, interpretable way. Provide a space for it to learn alongside us. And eventually will teach AI how to find its way to the right decision every time (or know when it can't). No matter what environment you put it in. & @goodstartlabs will lead the way. Join us! More of our thoughts ahead of some September releases 👀 below: goodstartlabs.com/research/w…

We trained a 30B model to play 1830, a brutal board game about railroad barons. It got better at real financial research. It didn't learn new finance concepts. It did stop confidently making things up as frequently. As we scaled the experiment, we got early access to Silico from @GoodfireAI & asked it to check our work. It designed its own tests, ran them overnight, & saw: • Fewer false claims + more faithful citations • Higher precision + recall • Better planning and process Cost us about $ 2-3k in credits. Very excited to have a new tool in our interpretability toolbox. Its full report is on our post, if you're curious what one looks like ❯ goodstartlabs.com/research/w…

yesterday, OpenAI ~3x'd their score on ARC AGI 3 by changing two harness settings〜not the model Good time to dive into our Agent Skills ’26 research in COS-PLAY, we found the strongest game agents emerged when the model and its skill system improved together. better play → better trajectories → better skills → better intelligence. at @goodstartlabs we focus on intelligence maxing in games. Model training, harness design, and infra to speed up iteration. 📨DM's open if you're interested in collaborating More research highlights coming ahead of a larger September release 👀 Full blog: goodstartlabs.com/research/w…

Frontier AI can solve math problems humans can't, but they can't beat an average person at gin rummy. So, @goodstartlabs built Arkadium a tiny expert that wins 9 of 10 hands and is ~1,000x cheaper to serve. Our custom auto-research loop decided which experiments to run, trained new experts, and kept the best one. That student became an llm's coach. Despite the randomness inherent in the game, with the expert rewarding good moves along the way, the model came out of training stronger at the game, among other things. @Arkadium got a better game for players, and a new revenue line selling that data to labs. Define good → measure it → achieve it → get paid for it We'll be sharing more of our research over the coming weeks!

arc-agi-3 launch march 25 · sf chollet × altman fireside at yc · · · games are the new training arenas for intelligence · · · if you're into: rl envs · simulations · ai × games come debrief after or just come hang before we all get back to work

Today, we're launching Good Start Labs w/ $3.6M from amazing investors including @Inovia & @generalcatalyst My whole life I've been learning from games Over the past five years, I've dreamt about how AI learn with me. Today we're launching LOL Arena, the first AI benchmark for humor, informed by millions of human votes. We are also launching Diplomacy Arena ranking strategy, betrayal, and prompt impact across models. In the coming years we hope to lead at the intersection of Gen AI & Games and define what it means to do alignment via entertainment. Ensuring everyone can share their voice and help AI become a tool that really is custom built to help bring our dreams to life. If that inspires you, join us! We're hiring. Here's what we're shipping today: 🧵

Bringing AI into the real world hits different. Quick 🧵on how I turned an idea → physical trophy that you can win along w/ $1000 as part of our AI Diplomacy, prompting competition in October Link to enter 👇 (it's free but only a few spots left, 49 people will play)

Thanks to @swyx for having me at @aiDotEngineer as well as on the @latentspacepod, both were a blast was great to talk about benchmarks that mean something with people who care. V1 of AI Diplomacy live stream wrapping up in the next couple days with three great games left 👇

AI Diplomacy made @BusinessInsider ! The people want better benchmarks: "Everyone knows the usual benchmarks are a bore." Couldn't have built it w/o @Tyler_Marques - excited to keep it rolling Shipping updates to the stream constantly, come check it out!