Then I want to shout at it "Is the work done? No it isn't so yes of course continue, are you stupid?", but then I remember it's basically a big matrix and for the 58th time type up "Yes, ultrathink and continue"

A junior developer would learn, claude doesn't. I've tried adding this to CLAUDE.md but it doesn't help.

I use claude to write a design, review the design, turn that into an implementation plan, spend 2-3 turns reviewing that, but still when that is turned into code it misses things or creates helpers that's not actually used or... It creates massive files and unless I explicitly tell it to it never refactors them. It often just silences errors and warnings instead of actually fixing the problem.

It saves a lot of time, and I'm building things I couldn't have on my own. But it makes a lot of mistakes, it's far far from one shots which the hype keep going on and on about. It's tricky to put firm limits on what it does. A lot of the mistakes I catch because I've spent 15 years without an agent and sometimes it's just "hm, this smells weird" and I begin digging. I worry about the next generation.

For me the mental framing of "It's all hallucinations, some of those hallucinations are useful" is helpful to keep frustration in check as I ask it to review the same implementation plan for the 4th time and it turns up different issues because the input was slightly different, or review the output code and see allow(dead_code) despite my claude.md forbidding it.

The valuation is insane and the very low float plus short timeframe for actual price discovery just seems built to extract money from index investors.

They can follow the same rules as everyone else.

Nasdaq clearly did it for the big bucks and getting the listing, why did Russell bend the knee?

But now he's also trying to get the indexes to pay for the giant cash fire called X.ai and the far right huddle Twitter too.

I have zero interest in owning anything of either of those companies.

Which is a damn shame because most juniors I've worked with are amazing and the most recent junior hire 1.5-2 years ago is so much better than I was their age it's almost embarrassing.

And my team is in an area termed "strategically important" before anything other than AI became an annoyance.

They didn't trade company fundamentals, they traded the market sentiment.

What do people recommend? I'm on Linux/Firefox/android and don't want to self host.

Now central banks will be in a bind.

But no, they waited 1-2 months or something until the regime could reload and people had gotten tired and went home to grieve for their dead friends and family. Then they started yolo bombing. Again.

Though you can probably post rage bait 500 tweets in that time. So maybe the overall point still stands when thinking about it.

For me it crashed after the first click in the menu.

Space Marine 2 was the latest one for me, but Steam is great at refunds if you do it quickly enough.

I'm surprised that one goes into a field as small and competitive as art history in these days.

Museums, how many relevant art related roles can there be nation wide?

1.5 years of basically no irl social life and going to bed at 22 every day has really hammered home my rhythm. I still wake up around 06-07 every day.