Haskell jock. Backend Developer UX at @mercury. I wrote @prodhaskell so you can get a Haskell job!
Denver
- Tweets 17,664
- Following 597
- Followers 5,460
- Likes 43,217
Pinned Tweet
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
11,272
yes, 100%. the most robust findings in education research all point to this, but no one wants to do it because of the cost and scaling concerns. fortunately it also the easiest for an individual family to implement via homeschooling
1
11
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
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
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
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
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
There is nothing good about Austin except the fact that some of the most interesting people in the world have chosen to gather there. Horrible circumstance.
Yeah bro you have to visit Austin. You can pay $40 for a food truck entree and eat it at a picnic table with flies everywhere. Misters spray water all over your food it’s 100 degrees
6
21
1,319
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
“Hey do you want to cut your salary in half and move to a shithole? Why aren’t you responding? This is my last attempt…”
2
16
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