Web dev (Python, Django, TypeScript, Vue), Founder, DJ. Documenting my learnings at til.unessa.net. Find me at the blue thing: @uninen.net
Joined January 2008
- Tweets 3,005
- Following 468
- Followers 433
- Likes 2,161
265 Photos and videos
Pinned Tweet
13 Feb 2021
I have two kinds of hobby code projects;
1) where I enjoy choosing my tools and writing everything as perfect and beautiful as I can,
and
2) where I’m just enjoying hacking or learning something, and also the fact that I can write as much spaghetti as I want.
I love both 😅
8
Jun 13
Even on this timeline this is the most ridiculous thing for a long time. Fable was at most marginally better than Opus in most tasks. US government is so fucking dumb 😂😂
Good Hello chinese distills ✌️
Jun 13
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: anthropic.com/news/fable-myt…
39
Jun 8
Been thinking about code, carpentry, and other crafts. Code is IMO definitely in "monkeys should not do it" category but hand-crafted carpentry still feels valuable over CNC-machined stuff.
Still, there's *something* in hand-crafted software that we shouldn't lose.
20
Jun 7
Two things I love most about working with LLMs;
1) it's immediately clear if your code is unintuitive or written in a non-obvious way as LLMs struggle with it no matter how much you try to document it
2) following best practices finally pays out in full 🎉
20
Jun 5
Claude Design model selector shows me Opus 4.8, Opus 4.7, and Opus 3 (!?) but not 4.6 -- which is the only usable one from the latest models 🤔
The product itself is not that great but the results I get from it are AWESOME. Superb tool for a talentless designer like me.
24
May 30
The killer feature of Pi is that it can modify and debug itself. All software should have this.
Would happily pay to be able to say "fix the ts/eslint/prettier/oxfmt Vue configs - format on save broke again" in VS Code and Zed. So annoying to waste hours on editor configs 😩
40
May 29
First few 5h sessions w Opus 4.8:
1) Extremely annoying and hard to work with due to unpredictable behavior. Ask it to "load plan implementation skill", it loads it and then starts using git and searching for plans, picking one *randomly* and just start doing stuff. (!!?!?) ..
1
1
53
May 29
3) it does feel marginally smarter, tho. Haven't found ANY real world tasks so far that it didn't know how to solve after letting it do its thing. I appreciate that it can dive extremely deep in a Sentry issue, pull relevant bits from two repos and prod db and then just "Fixed."
1
15
May 29
I feel like the greatest limitation is the Claude Code harness itself, it's just hands down the WORST available tool at the moment. Combined with ridiculous pricing and usage limits, Opus 4.8 won't be in my daily arsenal - gpt-5.5 is just better. But good for docs and plans! ✌️
1
56
May 27
Now that the of "You're absolutely right" is over, long live the era of "Actually, wait"
10
May 22
Feeling vindicated bc I never took the time to learn cookiecutter properly, always kept manual template repos.
Now I don't have to anymore; it's so fast to let GPT-5/low loose on a handwritten template repo and tell it exactly what you want 🎉
WKND project coming up!
23
May 21
Hands down the worst part of daily driving a finely customized Pi: going back to Claude Code feels like having to drive a Soviet Lada from the 80s 💀
45
May 14
I remember a time when Netflix had "share your logins with a friend" ads. Getting the same vibes with this Anthropic shit. They have enough corporate clients now to not care about smaller clients anymore.
CC is now by far the worst harness but Opus 4.6 is still my fav model 🤷♂️
42
May 12
It's bonkers to think back how AI workflows have changed in the last couple of years. Getting a function to copy-paste felt awesome a year ago before CC era started. No I'm bummed when _some_ of the code produced by a 80 min agentic session is sub-par 🤯
30
May 8
Slopping w Claude, part n
Me: hey Claude (Sonnet / High), wasnt this issue already solved?
Claude: nope
Me: properly recheck, what were the last commits about?
Claude: related but didn't fix this
Me: ok, fix it
Claude, ~1h later: the PR wont merge bc main has the code already 💀
36
May 6
Every few days my clanker learns something new that I'm impressed by. Today it managed to run a full ticket pipeline started from a vague "create a ticket" prompt via Telegram to a reviewed PR w steps like visual repro & ack ping via GH comment.
Multi-channel comms feels magic!
1
54
May 6
The full pipeline: "Create a ticket" -> GH issue -> triage -> bug repro (playwright, screenshot) -> research -> spec -> [approval] -> plan -> implement in PR -> review -> security review -> [ready ack]
12