Rendered at 17:55:06 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Xcelerate 29 minutes ago [-]
You ever read a work of literature with such flowery language that right after you've read a paragraph, you pause and realize you have no clue what you actually read, only to read the paragraph maybe a second or third time and have your mind space out again and again on each successive attempt?
Yeah, for me, that's what parsing huge volumes of LLM-produced text like "direct model calls as replaceable semantic workers" does to my brain. Maybe others don't really have this issue, but after any long output, I prompt the agent "Go back and decompress any LLM-speak in light of the higher level task goals. Eliminate deictic language."
The revised output documents are solely for my personal usage to expedite understanding. The LLMs can slowly converge on their own language for all I care; I retain raw agent output for future agent usage (to avoid the "lossy" problem the author mentions), but that doesn't eliminate the need for some intermediate translation I can use to actually help get my work done instead of spending hours attempting to understand what a "load-bearing pinned gate" is.
mikaeluman 12 minutes ago [-]
I don't get it. The skills and instruction try to make the answer more machine like on purpose.
Not humanising it...
People want the terse, matter-of-fact output. Not the conversational chatty verbose and bloated nonsense with gray words and jargon and terms like "blast radius"
alansaber 8 minutes ago [-]
The article lost me when it implied that verbose drivel is actually intrinsically superior rather than a way to hedge bets
alansaber 11 minutes ago [-]
Not sure what happened in the blog, but I quite enjoyed the mindmap in the right panel
kuberwastaken 8 minutes ago [-]
Thanks, I guess haha :P
Havoc 26 minutes ago [-]
> The problem is that these instructions are not applied after the model has finished doing the work
Seems like something fixable with a simple two step process. Ask it the thing. Then ask it to summarise the answer in simpler terms. More tokens and time aside that would check both boxes
kuberwastaken 7 minutes ago [-]
pretty much what I do, better yet ask it to boil it down in visuals in a simple webpage if it's a very large project
StyloBill 17 minutes ago [-]
Should be a harness feature actually.
acarlson1029 45 minutes ago [-]
[dead]
spwa4 8 minutes ago [-]
TLDR: This is an argument to get LLMs to answer in short, even code-like statements because you can exchange information quicker with an LLM that way. Cool!
Yeah, for me, that's what parsing huge volumes of LLM-produced text like "direct model calls as replaceable semantic workers" does to my brain. Maybe others don't really have this issue, but after any long output, I prompt the agent "Go back and decompress any LLM-speak in light of the higher level task goals. Eliminate deictic language."
The revised output documents are solely for my personal usage to expedite understanding. The LLMs can slowly converge on their own language for all I care; I retain raw agent output for future agent usage (to avoid the "lossy" problem the author mentions), but that doesn't eliminate the need for some intermediate translation I can use to actually help get my work done instead of spending hours attempting to understand what a "load-bearing pinned gate" is.
Not humanising it...
People want the terse, matter-of-fact output. Not the conversational chatty verbose and bloated nonsense with gray words and jargon and terms like "blast radius"
Seems like something fixable with a simple two step process. Ask it the thing. Then ask it to summarise the answer in simpler terms. More tokens and time aside that would check both boxes