Toutes les curations

6 curations · 1314 membres · fenêtre de 12 h, demi-vie 6 h, seuil 4 relayeurs

0liens
2tweets
88868posts lus
953auteurs
9209liens en base
1472 hde recul

Les tweets 2

Axe indépendant : repris sans regarder les liens.

1
J
Justin Lo @loresjpg · 01:37
Nice DeepSWE score! Does it survive a lowercase filename? Introducing MaxxBench: 89 DeepSWE tasks with small changes to the instructions or starting code. Same engineering problem, slightly different requirement. Models clustered around 74% on DeepSWE end up 23 pp apart. Good
6 relayeurs à 14 · il y a 4 h Voir sur X
Qui l'a repris
Ce qu'ils en ont dit
J
Julian Schrittwieser @Mononofu a cité · 01:37
Making novel variations of evals is very useful, public evals tend to get memorized!
Hamel Husain @HamelHusain a cité · 01:16
I see some are drawing the wrong inference from this study: they are focusing on this meta benchmark as yet another benchmark for model picking, i.e. open vs closed models, model families etc. That’s too narrow of an interpretation! You need to do your own private evals on
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex a cité · 08/11 22:00
holy shit, an art form of scientific grift next METR/Epoch/AA employee right here you all need to work on your epistemic hygiene
Ofir Press @OfirPress a cité · 08/11 21:26
GPT-5.6 Sol and Luna were built by roughly the same people using roughly the same infra, I don't think we can blame the 20 point difference in Luna just on memorization. There's something else being tracked here in addition to memorization. Maybe MaxxBench questions are slightly
Ethan Mollick @emollick a cité · 08/11 18:33
2
Pushmeet Kohli @pushmeet · 05:08
Across our projects @GoogleDeepMind, we are witnessing a genuine phase transition in the pace of scientific discovery. You will see a glimpse of this in our releases in the next few weeks.
4 relayeurs à 8 · il y a 9 min Voir sur X
Qui l'a repris
Ce qu'ils en ont dit
Ethan Mollick @emollick a cité · 05:08
It isn't that weird to think that "this time is different" - we had a couple of Industrial Revolutions over the past couple centuries, just because we got used to a relatively steady-state regime post World War Two with a regular pace of growth doesn't mean it continues forever.
Lucas Beyer (bl16) @giffmana a cité · 08/11 20:37
Pre-announcing the pre-announcement
Dr Singularity @Dr_Singularity a cité · 08/11 18:30
1000 scientific breakthroughs drop from Google incoming?