The Bitter Lesson - RL Environments Version
seancai.com · 1,079 words · saved by 1 readers
Read my thoughts on The Bitter Lesson - RL Environments Version
Let’s address the biggest qualms with data and RL env companies today: While realistic RL environments are needed to push performance today, the high cost of building & maintaining environments: realistic, high-fidelity simulations or replicas are expensive to develop and keep up to date. Successful RL environment startups will move building systems that reduce cost, increase reusability, and, through building 100s of RL environments, figure out automation in RL environment creation or some new insight about building verifiers more easily for strictly non-verifiable outputs. Look for startups
saved by
related reading
- Vikram Aditya (@viks_rum) on Xx.com
- Good QC for RL Dataseancai.com
- What if RL Environments Aren't Mispriced?benanderson.work
- Sweatshop data is overmechanize.work
- Trust me bro, just one more RL scale up, this one will be the real scale up with the good environments, the actually legit one, trust me bro — AI Alignment Forumalignmentforum.org
- RL Environments and RL for Science: Data Foundries and Multi-Agent Architecturesnewsletter.semianalysis.com
- Cheap RL tasks will waste compute | Mechanize, Inc.mechanize.work
- Training Imperativesdan.io
- Why are there so few independent eval startups?thomasliao.com
- Convictionconviction.com
- Pavlov's List: A List of RL Environment Startupspavlovslist.com
- A World of Verifiable Domainsseancai.com