mihaichiorean

I wanted to see how far I can get running a strong coding model - m2.5 from minimax - in an agentic loop on my dgx spark. What's not in the post yet: it's running, I gave it a project, completely hands off, used about 1.2m tokens.

I have a lot more learnings from this than I can put in 1 post. So this is the framing. I'll drill deeper into topics I've explored later.

I agree. he can be prosecuted for not reporting his spending probably, but as long as he didn't ship boatloads of fake ballots it doesn't warrant cancelling the election. the authorities should put a stop to the interference, and if the interference to influence was his advantage, the 2nd round, without interference, would have him lose. Just let the people vote.

I still believe that the main "problem" was that the front runner party that has been in the 2nd round for 10s of years and which has the prime minister as the candidate, didn't make it to the 2nd round. Someone wanted this fixed. Obviously the prime minister who was 3rd in the 1st round made declarations in support of the ruling.

I shipped something users (internal) loved and the users were pushing adoption across the company. My leaders didn't consider it shipped. They never talked to the users. Didn't care. It needed perfect alignment with the org and needed to help the org's plans. Not the company or users across the company.

I could have guessed this. I've advocated for workplace but Meta is too untrendy nowadays and people are too biased to accept that the feed, in a workplace scenario, is actually extraordinary. kudos to you 2!! rooting for y'all

this is pretty cool! will give it a go!