✳flâneur — a map of the web's best reading

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 Forum

alignmentforum.org · 3,596 words · saved by 2 readers

I've recently written about how I've updated against seeing substantially faster than trend AI progress due to quickly massively scaling up RL on agentic software engineering. One response I've heard is something like: RL scale-ups so far have used very crappy environments due to difficulty quickly sourcing enough decent (or even high quality) environments. Thus, once AI companies manage to get their hands on actually good RL environments (which could happen pretty quickly), performance will increase a bunch. Another way to put this response is that AI companies haven't actually done a good job scaling up RL—they've scaled up the compute, but with low quality data—and once they actually do the RL scale up for real this time, there will be a big jump in AI capabilities (which yields substantially above trend progress). I'm skeptical of this argument because I think that ongoing improvements to RL environments are already priced into the existing trend: I expect that a substantial part o

x 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 Forum AI Timelines AI Frontpage 2025 Top Fifty: 13 % 58 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 by ryan_greenblatt 3rd Sep 2025 9 min read 32 58 I've recently written about how I've updated against seeing substantially faster than trend AI progress due to quickly massively scaling up RL on agentic software engineering . One response I've h

Explore this link on the map →

saved by

related reading