Does anyone with 100 AI agents running simultaneously and $10k cursor bill actually ship?

At that point does it make sense to just invest in a local AI setup?

Good question

Do open source models compete with sota right now?

You can use Deepseek, Qwen, llama, via ollama locally. Or buy a beefy Mac mini/studio. I haven’t found it to be fast enough with what I have but it’s good to use OpenAI compatible things

Applied AI, databases, data, vibe coding (sic.), open source, community/devrel, remote. 

itinerant businessperson. globalist.

Nope. Llama is let’s just say not too impressive. Qwen is underrated. I haven’t tried the new Deepseek and I can’t comment on what mistral has given recently either. 

It’s pretty hard to beat Claude, Gemini, and ChatGPT frankly. This is “correct” as of today - this can change later of course.

Even if it were fast enough is it any good compared to the frontier rn?

Agreed. But I also don’t think many (including at faang) are spending anywhere near that amount on cursor.

It makes sense in my mind to be able to look at dropping 10s of thousands on a dedicated AI rig if it means potentially being able to offset a bill around 7-10k a month or whatever those timescales were