Which is illegal according to EPA regulations, last I knew.

Yeah, here we are.

3-6 active sessions on different work trees isn’t unheard of either

Agent loops for SWE burn a LOT of tokens.

I’m unfortunately temporarily disabled and can’t use my hands for another 2 months. So I’ve leaned heavily into AI based workflows to keep my job in the meantime.

Aside from the nightmare of keeping quality high, not atrophying skills, and avoiding a lack of domain knowledge. It works reasonably okay.

Token usage is insane though. A productive day might cost a few hundred dollars in tokens all things considered. Quality is expensive as well, a good 1/4 of that are automated systems that exist to identify defects, quality, coherence…etc issues early.

Mixed bag.

There are legitimately high value problems that AI works well against. But ungoverned proliferation has a net negative ROI across complex and difficult to measure areas.

When applied expertly, it works great. When blindly handed to your entire workforce as a panacea, not so much

I accidentally went to Google for the first time in months and was wtf’ing over how many results are sponsored.

The complaints about Kagi are valid, mostly, (there’s always that one guy that runs around complaining that Kagi uses Yandex). But damn I’ve gotten spoiled by the results and the ranking customization…