Comment by _hugerobots_
13 hours ago
Have a 5090, and yes it's very fast. But it's like the worst ADHD team member and requires constant supervision and review from larger models. It's context size on-card is good for super, suuuuuper shallow precision work. The gb10/spark on top of it, that thing can refactor enormous monorepo architecture. The time it takes the 5090 to compact, reiterate and execute a plan is often the same time as the gb10.
> it's like the worst ADHD team member and requires constant supervision
Perhaps consider some non-offensive language for your comparison?
could you not be like that? provide alternative language or go away. If youre offended, say so and be real. Noncommittal posits of personal preference are linguistic mosquitos of communication. on the flip side, how dare you disenfranchise a legitimate adhd perspective. one that i would say is entirely valid as someone functionally crippled by such plight. If you truly are offended, perhaps there is some truth you are reacting to preventing you from truly responding in good faith. words are lame like that ya? mine are as nauseating as your flyby ego droppings.