Skip Navigation

Posts
25
Comments
184
Joined
3 yr. ago

Scottish loon sometimes in Caithness, usually in Edinburgh. Likes rugby, F1, reading, cooking, and irn bru

  • Genuinely no idea. Which makes it even more terrifying. I suspect Copilot github stats

  • My management are measuring code written by AI as a metric, and expect it to go up...

  • Remember kids, consent is sexy. And The Borg don't ask!

  • That's why I have a 65" and sit barely 2m from it. Stick on a 4k Dolby Vision encoded file through Jellyfin. Looks fucking great!

  • Nice, hate cracking ebooks. The world needs more of this

  • until(original=new) { run convertOriginal }

  • Deleted

    Permanently Deleted

    Jump
  • And it will fuck up around half of even the simple formulas. This is really bad, and the idiots in charge should feel bad. Excel basically runs the world and they are about to fuck it up

  • Deleted

    Permanently Deleted

    Jump
  • LLMs lose context over a short session. They all have input limits. Very small input limits usually. Best it can probably do is suggest formulas for you based on your natural language, maybe some copy/paste. Which means it can beat a 9 year old, great news everyone! Or show a help article on pivot tables (which the help function already does!)

    Excel is very simple to work with, hence its ubiquity. LLMs also get shit wrong about half the time, way more than half with difficult things ime. Meaning they cost experienced operators time, a few studies are showing this now with coding. And are expensive as fuck. And slow as fuck. And reduce capacity for learning. Meaning they actually cap what excel can achieve, as the user won't grow at the same rate, renoving the one advantage excel actually has: the learning rate is phenomenal

    The C-Suite which insisted on this integration is basically an subservient idiot themselves at this stage who doesn't understand their product, their market fit, or their userbase. They should replace thenselves with an LLM

  • Deleted

    Permanently Deleted

    Jump
  • LLMs can't count. Can't add. Can't deal with actually large datasets

    How is excel a good fit for vibe-coding?

  • Nowhere close to any junior ime. Grads learn very quickly. Interns only job is to understand. Code academy career switchers understand requirements and will ask questions. Subservient AI does fuck all of any of those things

    They are more akin to yet another Rapid Application Development wave imo. Go see how the previous iterations have done. Lots are still with us (rails ftw!). I'll bet most will outlive LLMs

  • Have you tried to have a smart phone outside of Apple or Android? They are clearly operating as a duopoly at this stage, they need tackled

  • I'd suggest you get an i18n package for whatever language you are using and follow their conventions

  • Logs, logs, logs, you'll pour over logs anyway. Hands up anyone who has run GraphQL over anything but http? Won't be many. And then another show of hands please: who's written a basic request using http tooling instead? Bet there's tons!

    They threw away loads of tooling for the sake of vanity imo

  • If only that were true. They are intimately connected and to pretend otherwise is laughable to me

  • GraphQL makes this same mistake

  • How much will the fines cost vs paying these people I wonder? 200*25k is approximately £5m/annum. Come on £10m fine!

  • Don't be so sure. Very little of his net worth will be liquid. Meaning giving up a big chunk of something