Ville Säävuori @uninen

Web dev (Python, Django, TypeScript, Vue), Founder, DJ. Documenting my learnings at https://t.co/jr0MQcSW6F. Find me at the blue thing: @uninen.net koneoppiblogi.uninen.net Turku, Finland Joined January 2008

Tweets

3K
Followers

433
Following

469
Likes

2K

Ville Säävuori @uninen

20 hours ago

tired: teaser model launches 👎 wired: taking an evening for yourself to enjoy writing clean handwritten code wo clankers 🤘

0 0 0 14 0

View Details

Ville Säävuori @uninen

a week ago

Days w/o GH Actions incidents: 0. A workflow in a random small repo that runs Playwright in ci got stuck installing it and spent ALL my monthly CI minutes in one failed 6h run that never finished bc some network issue 🤦‍♂️

1 0 1 24 0

View Details

Ville Säävuori @uninen

2 weeks ago

@mikko @SpaceX literally INSANE

0 0 0 203 0

View Details

Ville Säävuori @uninen

2 weeks ago

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 ✌️

Anthropic @AnthropicAI

2 weeks ago

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

13K 26K 88K 92.0M 24K

0 0 0 41 0

View Details

Ville Säävuori @uninen

3 weeks ago

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.

0 0 0 20 0

View Details

Ville Säävuori @uninen

3 weeks ago

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 🎉

0 0 0 20 0

View Details

Ville Säävuori @uninen

3 weeks ago

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.

0 0 0 24 0

View Details

Ville Säävuori @uninen

4 weeks ago

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 😩

0 0 0 40 0

View Details

Ville Säävuori @uninen

4 weeks ago

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 0 0 56 0

View Details

Ville Säävuori @uninen

4 weeks ago

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 0 0 15 0

View Details

Ville Säävuori @uninen

4 weeks ago

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 0 1 53 0

View Details

Ville Säävuori @uninen

a month ago

Now that the of "You're absolutely right" is over, long live the era of "Actually, wait"

0 0 0 10 0

View Details

Ville Säävuori @uninen

a month ago

@badlogicgames as long as we still see if it was a partial or full read. that is kind of importan info to know as some models do idiotic things like read 200 lines of a 500 line skill and then keep failing bc they missed most of the instuctions 🫠

0 0 0 178 0

View Details

Ville Säävuori @uninen

a month ago

Pretty apt commit message typo: update kills

0 0 0 9 0

View Details

Ville Säävuori @uninen

a month ago

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!