tolugenius

Curious on two things

1. How often do you encounter false positives, and does that change things?

2. Have you considered outright prohibiting/banning vs disclosure?

Just want to hear from someone running a platform how they deal with this since I imagine it's very hard to get right.

There is probably far, far more people trusting benchmarks and "I remade x thing in 1 prompt with y model" claims than you'd imagine, just ignore all of it. You know your workflow and what better should be and could be, measure on what works for you. You should note (and I may be wrong, not active in these part) a lot of those demos are very toy, recreating a known game, known app, known workflow, etc. very interesting but again a very toy example that should be taken with that in mind.

thanks!

Do you mind sharing them and what they do?

I wonder what would "compute" mean if cpus were more efficient at matrix multiplication say 15 years ago. And on the flipside, what it would take to say train a frontier model entirely on cpus in the future.

Original: https://www.wsj.com/finance/stocks/how-to-know-when-the-ai-b...

Archive: http://archive.today/bx6Dc

I did the default arithmetic with PetitGPT research-v1

>What is 2+2?

Answer

> To find 2 + 2, we need to add 2 to both sides of the equation.

> 2 + 2 = 4

> So, 2 + 2 = 4 + 2.

Brilliant

Feeling behind is natural, there's far, far more tools out there than accounted for. The main thing is to ask yourself how do you work and what's needed for your goals, projects, etc. I'm personally not quite there is letting the ai go autonomously, like if I'm working on paper I have it connect to zotero so I have a list of what's being cited. I think a lot of tools are bogus, you can go far with just model file + llama.cpp + tmux is just getting something running, obviously making a skill can automate some aspects of what the model does but remember models are not deterministic by nature.

My advice is find what you'll actually use and ignore the rest, I don't use a lot of skills or plugins really, maybe I could sit down and make 1-2 just thinking on it but really can't be asked. If someone tells you you're behind always remember in 2026 there are far more people globally who's biggest concern is if they'll have food to eat, running water, or working lights not "should I just the latest openai or anthropic model"

Archive: http://archive.today/jUrEr

This leaves me two questions 1. Will we ever reach (or have we already) where we can more empirically measure the cost of the adding the nth agent. Like the way businesses of different sizes can know when the nth employee add diminishes returns overall, can we measure the front with agents depending on task scope, resources, and other factors.

2. On the other end, can we see point where we can reduce how many agents are needed down the minimal set? For example many chains have reduced staff down to the minimal number of employees (note I do not agree with this) and still the balance sheet is in the black. I think in the hyper optimization and efficiency society we're in I think this will also happen, although the reality of "I can do 100 agents work with 10" might not be in providers and labs best interest economically.

Archive: http://archive.today/7RPo3

> If you believe these issues should not be raised because FLAWED was critical of OpenAI, please know that research is not sports. OpenAI is not the Spurs, 1Password is not the Knicks, and Off-by-1 Labs is not Jalen Brunson.

Got a hearty laugh out of this.