The Communication Cube


The Brazilian National Archive has publicized records of UAP sightings. Registering is free. After login mouse over "Favoritos" in the top menu and click on "Objetos Voadores Não Identificado".

Screenshot 2025-07-20 151315.png
 
The problem with LLM written code is that you can't trust it. It will hallucinate dependencies (with security risks) and is prone to writing unsecure code. So you need a human to review it. And code review is difficult, and not very interesting. It's like having a self-driving car but having to stay alert and ready to take control because it can randomly fail at any moment. You'd probably rather drive.
Ok. That sounds like what a decent coder would say.
Now, in the other hand, if you'd be a pointy haired CEO ... why not trust the LLM service your code, your database and your devops ? That's innovation !
I guess you all know my feelings about service as a software substitute and vibe coding, so the read was fun, and se non è vero è ben trovato.
SaaStr CEO first week of vibe coding for Replit's profit.


You actually want it the other way around: you drive and the car warns you if you miss something. And my limited experience with LLM-assisted code review wasn't very conclusive.
Well, some people with deep enough tongues and deep pocketed contacts are probably right now in a city near you planning to start a startup hiring 3D printed robotaxis from a LLM generated blueprint and paperwork run by the same chatbot running the customer support.
The control software in the robotaxi will likely be generated by itself from training in a virtual reality footage generated by a browser agent playing grand theft auto for many hours. And the only question the investor will probably have is :
- But did Rockstar agree to the plan, or are we doing it without them noticing ?
- Your second guess is right. As a contingency plan, we plan on adding a lawyer persona to our compliance/customer support chatbot.
- I see that's all well thought out, how much money are you asking for this round ?
There are some tasks where LLM could help (what TeDaDeS calls "Advanced Find&Replace" and extended autocomplete) but in my experience you'd be better off with a dedicated script/program/IDE extension for this. I actually had this in my last job: some of my colleagues were using LLM to write boilerplate code but I wrote a script that did the job in a far more reliable way.
Well, I guess that depends on how we look at it. Replit's bots have spared some suffering from the staff SasStr would have hired. Not sure any salary is worth having such a boss...
 
The story I'm currently working on using https://perchance.org/8m0lggwaza is turning out to be a wild ride (as most of my stories seem to end up being).

The story so far:
  • Two women get kidnapped (Tina and Sandy)
  • The police rescue the women
  • The women buy an apartment
  • One of the women invents something that makes them a lot of money
  • They buy a large house in the countryside
  • Their favourite dog (Mike) gets old so they put their money into life extending medical research
  • Research happens
  • A serum is created that rejuvenates the dog
  • More research happens
  • A serum is created that rejuvenates the women. If they keep taking the serum on a regular basis then they will never age
To do:
  • Thousands of years in the future the women set up a colony on an extrasolar planet
In other news, the AI model that the story generator uses really likes the surname Castellenatos (can't remember the exact spelling). I ended up with three of the folks in one story, and at least one in a few other stories.
 
I changed the battery of a Pixel 7 not too long ago. Shortly after I am informed that the bottom speaker isn't working. The speaker that I had to go through to get to the battery. So I order another set of sealant and open the thing again thinking I must've messed something up. While having it open I switch the phone on to test the speaker. That's when I am informed of a new update and whaddayaknow after installation the speaker now works again.
Ignoring the sense of guilt and procrastinating just a little bit longer would have saved me quite some work.
 
@kuru That's what you get from applying Occam's Razor. Or maybe it is that Occam's Razor is meant to not advise the answer, that needs the least amount of assumptions, but the one that induces the least amount of effort?
 
@kuru That's what you get from applying Occam's Razor. Or maybe it is that Occam's Razor is meant to not advise the answer, that needs the least amount of assumptions, but the one that induces the least amount of effort?
If you think about the effort required to prove those assumptions you're right both ways.

Has anyone here tried black frame insertion? On Handhelds? On PC? I'm curious since my PC screen can do many frames. And I'm still in the market for a handheld - maybe getting one with a 120 Hz screen is worth it.
 
Last edited:
If you think about the effort required to prove those assumptions you're right both ways.

Has anyone here tried black frame insertion? On Handhelds? On PC? I'm curious since my PC screen can do many frames. And I'm still in the market for a handheld - maybe getting one with a 120 Hz screen is worth it.
Supposed this handheld supports it: AYANEO Pocket EVO, and this one: AYANEO Odin 2 Portal.
But I never tried myself.
 
Back
Top