Another quote in today’s context :) would be

Dr. Ian Malcolm: God creates dinosaurs. God destroys dinosaurs. God creates man. Man destroys God. Man creates LLMs.

Dr. Ellie Sattler: LLMs eat man. Data centers inherit the earth.

Apparently, there's also an illustrated childrens' book by another author Sandra Peterson based on cyberselfish by Paulina [1]

[1] https://www.amazon.co.uk/dp/B0HF8QPPLS

edit: update to mention the new book's author.

Strong smell of Ai generation on the cover there.

Her agent says they can use the Cyberselfish part of the title but not her name. She was made aware of it a few weeks ago.

Trademark, rather than a trade dress issue. https://www.greenbergglusker.com/publications/when-copycats-...

>> I am pretty smart

Then listen to someone who’s wise!!!

>> Look at some of the shit John Carmack now says for God's sake.

Not questioning but can you share a few so that it can serve as warning reference.

What a delusional world we’re heading towards. :(

Before AI, most of the code was already crap and slop.

After AI, the volume of that crap and slop has increased exponentially.

This definitely helps and honestly should be done even the job isn't toxic! If for any reason sports is not possible, brisk walking is very effective as well.

I'm using AI only to clean up all the accidental complexity in the legacy projects at work that I'm paid for (this is in all C++ and Python productized from a Lisp prototypes, the latter hasn't needed that!).

Outside of work, I've stopped using AI completely in all my side projects which is very counter intuitive because even this limited use of AI at work exhausts me. This has given me a nice balance, so I do hand craft code in side projects which keeps that (now considered legacy) skill alive in case the bubble pops and we go back to old ways!

Sorry to hear about the job loss.

>> They're clearly not smart people

Nope, they're cunning and if it offers you any solace they usually lead miserable lives which is also a natural outcome.

this is what I often hope, that this must reflect in one form or another in their actual lives, and hopefully, has some form of consequence there.

Just this one line in AGENTS.md has given better results to reduce if not eliminate verbosity and grandeur.

**Always use ASD-STE100 Simplified Technical English

Disclaimer: I saw this listed in some other HN post that I can' locate right away.

This is probably the skill you remembered: https://github.com/AminBlg/SimpleEnglish

I have been using it for a few weeks, and it significantly improves the quality of the docstrings and code comments, as well as the readability of spec docs.

I have also added a few key bullet points to my AGENTS.md and have found the results to be very effective and generating plans and code that looks like something I would have written:

-----------

    ## planning, design and spec docs

    - the highest design goal is simplicity -- in our systems and our mental model -- even if if means edge cases are unaddressed and could potentially fail
    - please practice "ya ain't gunna need it" (YAGNI) do not add unnecessary guardrails
    - do not plan to add caching, many layers of unnecessary abstraction or other premature optimizations
    - look for places where adding or clarifying an invariant would simplify the code or the overall system

    please specifically try to avoid:

    - redundant calculations or duplicated work
    - duplicated conditionals or state-machine logic
    - storing state that can be derived from other state, which could drift and become out of sync over time
    - leaky abstractions across layers of the application
    - multi-line comments explaining a variable name or a single statement. well chosen names and design should makes these unnecessary, as the code is self-documenting

idk who came up with it first, but ASD-STE100 has been floating around more since matt pocock put it in one of his skills

This will produce quite verbose prose. STE100 is good for specs and explanations but it works best with a glossary or terms. will burn tokens.

This has not been my experience at all. I have been using this skill[0] for several weeks and when I ask it to rewrite existing AI slop docstrings to use this convention they are nearly always 10-20% smaller, plus easier to read and mostly free from the traditional "tells" of AI writing.

[0]: https://github.com/AminBlg/SimpleEnglish

Do you give the model access to the ASD-STE100 spec for reference/review or are you just assuming that enough of it is baked into the model for it to mostly adhere to it?

Agreed. ASD-STE100 makes automated code reviews tolerable.

If we alter the way LLMs talk, will it noticeably affect the quality of code it produces?