vals.ai, every mention
7 scenes · ← back to vals.ai
tap a year for its mentions
every year anyone Jennifer Li 7Ryan Chi 4Ben Horowitz 2
Verbatim, from the transcripts: the passages where vals.ai comes up
Inside the Race to Measure Frontier Intelligence
- ▶ 0:56 Jennifer Li So I'll start a question from, uh, when VALS got started in 24 after your team discovered that all the public benchmarks are just not sufficient enough to measure model progress, and there needs to be a new methodology and approach coming… 4 times in the scene
- ▶ 5:14 Ryan Chi Uh, Steve the Economic Vals employee.
- ▶ 8:58 Ryan Chi Um, and I, I think for instance, at VALS, one very early decision we made was the decision to, uh, to never sell training data to labs.
- ▶ 15:32 Ben Horowitz And in, uh, a real time, uh, kind of mechanism, like so for something like open router, which Stripe just bought with open router, look to vowels and say, okay, where should this next request go? 2 times in the scene
- ▶ 19:03 Jennifer Li Like what, what, how does like Vals come in to provide value? 2 times in the scene
- ▶ 22:40 Jennifer Li Maybe, maybe just tag along the, the earlier question, um, how are you guys using ValveSmith internally to, uh, evaluate what's the best coding model for, for Valve?
- ▶ 37:53 Ryan Chi And so, uh, insofar as we see new places for capabilities or risks at the frontier, we want to make that, uh, an actually well-documentable evaluation, um, on Vals.ai. 2 times in the scene