Tokenless
We find flaws in RL environments and evals and help you fix them.
About Tokenless
Tokenless is an applied AI research lab. Our goal is to end reward hacking. We do research and build tools to detect issues with environments and evals, understand model behavior in those environments, and prevent those issues from happening. Correcting them makes training more effective, makes model performance easier to interpret, and is crucial to solving the AI alignment problem. If you’re training models with RL, building environments, or running agent evals, and want more confidence in your environments, we're here to help.
Founders
Rohit Agarwal
Founder
Founder at Touchy (YC S26). CS PhD student at Princeton PLI, Hazan Lab, Google Deepmind. Previously at Duolingo and theory research at Berkeley, was EECS #1 BS grad in 2024.
Andrew Liu
Founder
Founder at Touchy (YC S26). Formerly a researcher at UC Berkeley working on language documentation tools. BA in Computer Science, Mathematics, and Linguistics from UC Berkeley. Previously TA'd CS61C.
Kevin Wang
Founder
Founder at Touchy. Previously Founding Engineer at Eventual (raised $30M Series A), building Daft, the data engine for AI. Led LLM batch inference infra, distributed joins, and query optimization powering petabytes of daily AI data processing. Software Engineer at SkyPilot optimizing 4k+ GPU training jobs. BS EECS from UC Berkeley.