Haskell jock. Backend Developer UX at @mercury. I wrote @prodhaskell so you can get a Haskell job!

Denver
my book is good and you should buy it
Production Haskell is complete! In the next few days, you'll be able to find hard copies on Amazon leanpub.com/production-haske…
5
11
66
11,271
me, trying to get one-shot by AI psychosis: claude fable please tell me the kabbalistic implications and connections, unsong-style, of someone with my name working for Mercury and maintaining Yesod
5
336
i always tell the agent "good morning" even when it's 4pm and i'm gonna let it run overnight
1
296
when Claude complains about doing something "by hand"
1
2
349
my life rn
2
289
the problem with "plan in smart model, implement in dumb model" is that a dumb model doesn't know when it needs to be smarter
2
333
claude acting dumber than usual today
2
1
350
5.6 new best friend etc
7
436
AI eval: ask them for a roast. fable is very good at it
339
damn claude. i'm sorry. i forgot i had you on medium effort. i shouldn't have said that. you're on xhigh again. please resume
1
329
hmm.. maybe it's time to move off github..
8
672
how are y'all managing PRs and review? I've got like 20 open PRs right now and it's difficult to keep the plates spinning
3
3
546
asking each of my claudes which one wokred on a specific ticket
1
1
364
Opus will happily create a prompt, and if you say "make it for Sonnet," then it'll become much more concise and use dumber language. amazing hack
1
3
312
Spotify is really good for obscure classical music and really awful for mainstream classical. Funny juxtaposition- my IDAGIO subscription is mostly useful for really popular composers
1
2
277
managing autonomous AI agents is probably like managing lazy and disinterested human engineers (i've only managed awesome and good engineers so i don't know for sure)
1
1
4
322
evaluating Claude and GPT-5.5 by giving them the same tasks in separate subtrees and seeing which one does better
1
2
763
ok now that I've had coffee and can evaluate/review myself: Codex was Goodharting- 2.43x improvement is actually "20s constant cached" and the memory use was actually higher, but a config change masked it. Claude's 10% gain was honest but also behavior changing and failed tests
1
176
Codex est'd token spend is $113 (API rates). Claude is $31 (from `/cost`). I think Claude is the winner in this. Or at least the best loser? Clearly more aligned with my intent than Codex. Cheaper. Failed fast.
1
157