Talk like Paul Dirac – fewer words is better
This is the entire contents of my home dir AGENTS.md file now.Does it help reduce the slop you have to read for you the same way it feels like it does it for me?
asen
Re:Talk like Paul Dirac – fewer words is better
on Monday October 19, 2026 @04:47PM (#50157836)
fun thing is that of course it will forget it in a long session and spit some too long text. but just typing `dirac` makes it recall the instruction and shorten it
Re:Talk like Paul Dirac – fewer words is better
on Sunday October 18, 2026 @07:15AM (#50139994)
Thanks. And maybe I am wrong, but I feel that Paul Dirac should be better represented in the weights than Attempto Controlled English, which sounds niche to me - or at least - I hear it for the first time.
Easy for anyone to try out themselves, and my post is only half a joke - it actually works. For me, at least :)
Re:Talk like Paul Dirac – fewer words is better
on Saturday October 17, 2026 @11:54AM (#50132189)
The reason i believe is good is because with very few tokens you encode two properties, for which Paul Dirac is most famous for.
* a great scientist (which hopefully encourages researching and verifying answers)
* a person who doesn't like to use many words at all
The later hopefully compensates the apparent "output-prose-greediness" most models seem to have. No idea if that "token greedines" (or slop) is a result from the companies business models or inherent for the models and their training :/
Re:Talk like Paul Dirac – fewer words is better
on Saturday October 17, 2026 @10:17AM (#50131404)
Agreed, thanks! This kind of makes it obvious that I am not a native speaker, but kind of also proves its was not written by an LLM :)
Edit: fixed now: less words -> fewer words
Re:Talk like Paul Dirac – fewer words is better
on Saturday October 17, 2026 @09:33AM (#50131043)
this is an instruction for LLM, not for people
Re:Ask HN: Tool Calls vs. Structured Responses
on Tuesday December 02, 2025 @06:10AM (#46120044)
Thank you for the response!
Ask HN: Tool Calls vs. Structured Responses
Hi, I feel like everyone is building LLM Agents (and Agent frameworks) recently and I would like to know what approaches people prefer when building these:* Tool Calls - give the LLM the tools and let it figure out the details* Structured responses - ask the LLM to give you all the details in one shotI can imagine that each approach has specific use cases (and "combination of both" is likely...
Re:The history and evolution of an alternative monitoring system
on Sunday January 16, 2022 @05:29AM (#29954838)
Link to the github project: https://github.com/asen/smg
The history and evolution of an alternative monitoring system
Re:Time Series Databases to Watch
on Saturday May 04, 2019 @01:57PM (#19828050)
Here is an example: https://github.com/asen/smg (I am the author)