Flutterby™! : Still adding LLM features to work

Next unread comment / Catchup all unread comments User Account Info | Logout | XML/Pilot/etc versions | Long version (with comments) | Weblog archives | Site Map | | Browse Topics

Still adding LLM features to work

2024-12-17 00:45:02.835069+01 by Dan Lyke 2 comments

Still adding LLM features to work project. Still having the "dancing bear" reaction and not happy with what I can prompt ChatGPT 4o to give me.

Anyone have a "smart person's guide to prompting LLMs" suggestion? I'm already cueing it to give me extra stuff in machine readable form, but it all seems like such bad SEO inspired insipid elementary output, and, of course, gets facts wrong.

So how are people seeing these things as valuable, and getting useful output?

[ related topics: Work, productivity and environment Douglas Adams ]

comments in ascending chronological order (reverse):

#Comment Re: Still adding LLM features to work made: 2024-12-17 03:37:22.241459+01 by: spc476

I think it's the crazy pills.

#Comment Re: Still adding LLM features to work made: 2024-12-17 20:05:40.235618+01 by: Mars Saxman

The only professional use I have made of an LLM came about when I needed to write a readme for a piece of software we were about to publish. I asked ChatGPT to do the job for me, and it promptly spewed a lot of convincingly plausible bullshit in the form of a typical readme file. After chuckling over this, I rewrote it all - but having the skeleton there to get started on was genuinely useful.

The impression I have gotten about coding LLMs from the people who swear by them is that they are helpful for problems I don't really have. Next-level autocomplete sounds great and all, but I don't even bother with conventional autocomplete!

Add your own comment:

(If anyone ever actually uses Webmention/indie-action to post here, please email me)




Format with:

(You should probably use "Text" mode: URLs will be mostly recognized and linked, _underscore quoted_ text is looked up in a glossary, _underscore quoted_ (http://xyz.pdq) becomes a link, without the link in the parenthesis it becomes a <cite> tag. All <cite>ed text will point to the Flutterby knowledge base. Two enters (ie: a blank line) gets you a new paragraph, special treatment for paragraphs that are manually indented or start with "#" (as in "#include" or "#!/usr/bin/perl"), "/* " or ">" (as in a quoted message) or look like lists, or within a paragraph you can use a number of HTML tags:

p, img, br, hr, a, sub, sup, tt, i, b, h1, h2, h3, h4, h5, h6, cite, em, strong, code, samp, kbd, pre, blockquote, address, ol, dl, ul, dt, dd, li, dir, menu, table, tr, td, th

Comment policy

We will not edit your comments. However, we may delete your comments, or cause them to be hidden behind another link, if we feel they detract from the conversation. Commercial plugs are fine, if they are relevant to the conversation, and if you don't try to pretend to be a consumer. Annoying endorsements will be deleted if you're lucky, if you're not a whole bunch of people smarter and more articulate than you will ridicule you, and we will leave such ridicule in place.

Flutterby™ is a trademark claimed by

Dan Lyke
for the web publications at www.flutterby.com and www.flutterby.net.