• 9 Posts
  • 62 Comments
Joined 1 year ago
cake
Cake day: June 18th, 2023

help-circle
  • I have experienced this myself.

    My main machine at home - a M2 Pro MacBook with 32GB RAM - effortlessly runs whatever I throw at it. It completes heavy tasks in reasonable time such as Xcode builds and running local LLMs.

    Work issued machine - an Intel MacBook Pro with 16GB RAM - struggles with Firefox and Slack. However, development takes place on a remote server via terminal, so I do not notice anything beyond the input latency.

    A secondary machine at home - an HP 15 laptop from 2013 with an A8 APU and 8GB RAM (4GB OOTB) - feels sluggish at times with Linux Mint, but suffices for the occasional task of checking emails and web browsing by family.

    A journaling and writing machine - a ThinkPad T43 from 2005 maxed out with 2GB RAM and Pentium M - runs Emacs snappily on FreeBSD.

    There are a few older machines with acceptable usability that don’t get taken out much, except for the infrequent bout of vintage gaming

















  • I do not agree with @FiniteBanjo@lemmy.today’s take. LLMs as these are used today, at the very least, reduces the number of steps required to consume any previously documented information. So these are solving at least one problem, especially with today’s Internet where one has to navigate a cruft of irrelevant paragraphs and annoying pop ups to reach the actual nugget of information.

    Having said that, since you have shared an anecdote, I would like to share a counter(?) anecdote.

    Ever since our workplace allowed the use of LLM-based chatbots, I have never seen those actually help debug any undocumented error or non-traditional environments/configurations. It has always hallucinated incorrectly while I used it to debug such errors.

    In fact, I am now so sceptical about the responses, that I just avoid these chatbots entirely, and debug errors using the “old school” way involving traditional search engines.

    Similarly, while using it to learn new programming languages or technologies, I always got incorrect responses to indirect questions. I learn that it has incorrectly hallucinated only after verifying the response through implementation. This makes the entire purpose futile.

    I do try out the latest launches and improvements as I know the responses will eventually become better. Most recently, I tried out GPT-4o when it got announced. But I still don’t find them useful for the mentioned purposes.