Login
You're viewing the assemblag.es public feed.

Replies

  • Simon Michaelsimonmic@fosstodon.org
    Mar 2, 2026, 2:21 AM

    PS no denying there is (will always be) slop. But if you look again at rustledger, you might be impressed. Beyond the usual type checks and extensive test suites it also includes TLA+ formal verification of some functionality.

    💬 0🔄 0⭐ 1
  • CyberFrogfroge@social.glitched.systems
    Mar 2, 2026, 6:30 AM

    @simonmic@fosstodon.org I did see the verification, it's interesting but my critique of AI is less about the actual code at any given snapshot in time, and more about the way it's produced, the lack of oversight developers give it, and the fact that this leads to many bugs and errors being added over time.

    A lot of the reason I'd probably avoid these projects is that I'm not sure if they will create regressions tomorrow, or next week, due to some massive set of AI changes with poor review, who's to say they won't just break the TLA+ tests? I have much less confidence in the developer's ability to push stable and reliable changes, and this is a pretty big red flag when their programs are supposed to handle my financial future...

    💬 0🔄 0⭐ 0
  • Simon Michaelsimonmic@fosstodon.org
    Mar 2, 2026, 7:29 AM

    I think if you look at #rustledger (just as an example) right now you'll see the oversight and quality is pretty high. Why shouldn't it stay that way ? Isn't this a counterexample to what you're saying ? My 2c: not all use of AI is the same; not all of it is vibe coding; and projects where AI is used in some way, don't have to be low quality.

    💬 1🔄 0⭐ 0
  • Simon Michaelsimonmic@fosstodon.org
    Mar 2, 2026, 7:42 AM

    This aside, I understand the wish to have your accounting be on a rock solid foundation - I feel the same. No software is perfect, but you can still achieve it: keep your data, and if you need extra assurance, your reports, in version control; use double entry bookkeeping; regularly reconcile with real world balances; and perhaps run extra correctness checks. (#plaintextaccounting FTW.)
    It is now very hard to miss any mistake made by your software - you'll see and address it right away.

    💬 0🔄 0⭐ 2
  • Caleb Maclennanalerque@mastodon.social
    Mar 2, 2026, 7:07 PM

    @simonmic I submitted some fixes to rustledger and the maintainer rehashed them through an LLM that botched them. I sent corrections that were either hand applied or more strongly hand-held. Then the next day they regressed again because claude didn't like my fixes and reverted them while austensibly working on something else and the maintainer didn't even notice the unrelated changes.

    💬 0🔄 2⭐ 1
  • 💬 0🔄 0⭐ 0
  • 💬 0🔄 0⭐ 1
  • Robin Syl 🌸:blobcat_box: :heart_nb:robinsyl@meow.social
    Jul 1, 2026, 9:25 PM

    @froge No like genuinely it's so bad. I've been using Actual as a replacement for YNAB, up until they used my donation money for a Claude Code subscription. I decided to look for a replacement, and there are basically *no feasible options that haven't started vibe coding*. I think something about finance makes you more prone to LLMs.

    💬 1🔄 0⭐ 0
  • eclexictheeclecticdyslexic@mstdn.social
    Jul 2, 2026, 12:07 AM

    @robinsyl @froge considering the whole thing is driven by finance you might be onto something. I think they are designed specifically to impress VCs, which probably has the side effect of impressing bean counters at a disproportionate rate to the rest of the population.

    💬 0🔄 0⭐ 0
  • 💬 0🔄 0⭐ 0