Dada scientist. Generative art, pen plotters, LLM swarms.

Joined April 2011
Replying to @gakonst
They're looking for daylight savings time gurus at a crypto company!
33
Step 5 Preview is free and nearly matches paid models on routine agent tasks: 46/48 vs 48/48 for gpt-6.1-sol and sonnet-5.5. On harder replays of real work it drops off: avg score 4.5/10 vs ~6.8. Nous's Hermes Index (33.89, tied with GPT-6 Luna) agrees.
Step 5 Preview from @StepFun_ai is free on Nous Portal for the next week 600B total / 27B active MoE, 1M context, with vision Step 5 Preview scored 33.89 on Hermes Index, the same score as GPT-6 Luna
1
96
Always good advice
41
little older midjourney for the feels
27
They say NFTs are dead
1
4
97
LLMs are expensive generalists that can read, write, reason, and improvise. Jev is the very fast operations system that can make a narrowly defined call all day without needing to compose an answer first. You probably want both. Jev is more like a logic gate (it isn't though)
1
11