Remix.run Logo
abixb 6 hours ago

>I think that the harnesses and context management is really where the rubber meets the road, and the real gains are happening there.

True. So we did hit a wall with pure scaling alone, though no lab would admit it. It's crazy to see how harness switchout results in such vast delta in benchmark scores.

XenophileJKO 2 hours ago | parent [-]

We have not "hit a wall" by any stretch yet. I don't understand how someone can even hold this viewpoint? It's mind boggling.

Harnesses magnify and make the intelligence actionable, but we have not reached limits on raw intelligence yet, not even close.

senordevnyc 2 hours ago | parent [-]

Agreed. Trivially observable by using a frontier model from today and one from 6 months ago with the same harness.