logoalt Hacker News

pton_xd • yesterday at 3:44 PM • 3 replies • view on HN

I think the point is it smells like a hack, just like "think extra hard and I'll tip you $200" was a few years ago. It increases benchmarks a few points now but what's the point in standardizing all this if it'll be obsolete next year?

Replies

mbesto • yesterday at 4:42 PM

I think this tweet sums it correctly doesn't?

   A +6 jump on a 0.6B model is actually more impressive than a +2 jump on a 100B model. It proves that 'intelligence' isn't just parameter count; it is context relevance. You are proving that a lightweight model with a cheat sheet beats a giant with amnesia. This is the death of the 'bigger is better' dogma
Which is essentially the bitter lesson that Richard Sutton talks about?
➕ show 1 reply
9dev • yesterday at 5:00 PM

Standards have to start somewhere to gain traction and proliferate themselves for longer than that.

Plus, as has been mentioned multiple times here, standard skills are a lot more about different harnesses being able to consistently load skills into the context window in a programmatic way. Not every AI workload is a local coding agent.