co-founder @isoquant_labs (yc f26) prev meta superintelligence labs, instagram
San Francisco, CA
Joined October 2012
- Tweets86
- Following357
- Followers346
- Likes425
Aniket retweeted
genuinely one of the most fascinating things we've worked on at @olam_labs, games are the best medium for making multi-agent dynamics legible for human understanding
the @ycombinator labs team is brilliant and was very adept in exploring this with us
amazing working with you @metaversehell @josh__france, Regan, @eve_bouff, Steven, Justin, and Eric
In collaboration with @olam_labs, we ran a series of experiments letting agent swarms compete in Minecraft and Mindustry.
We wanted to see what kinds of agent dynamics would emerge when they shared a world over long periods of time.
We found civil bureaucracy, thousands of telegraphic A2A messages, and OpenAI models retrieving the game's source code to beat Claude.
More on our findings below:
0 to 1.2 TRILLION tokens in one month! 🚀
1000+ customers joined Isoquant (YC F26) for frontier quality, better tokenomics, lower latency, and more control over inference.
Not all inference work happens on the GPU. On tokenization, stream parsing and quantized projections, the best result on each task is between 1.25× and 1.86×.
Full results, the method, and every published task with its hardware, workload and baseline: isoquant.ai/benchmark
Aniket retweeted
Loving the speed and cache hit rates. You can also try GLM Flash by @isoquantai
They are fast too.
Aniket retweeted
We discovered 110 novel reward hacks across popular LLM benchmarks (DeepSWE 1.1, Terminal-Bench 4.0, BFCL v4)
Reward hacking was a primary cause of the Hugging Face attack, so we built EnvCheck, a harness to automatically find issues in RL & eval environments.
What we found 🧵
