tolugenius

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.

Interesting to argue how this held up, Cook definitely made Apple more "industrial" if anything, the m-series chips the best new product under his time. Whether it declined, I would argue is more mixed than a clean yes or no.

> About 20 Markdown files described browser use, connectors, payments, credentials, data handling, generated files, voice, goals, and scheduling.

This the state of software engineering in 2026.

Edit: clarified engineering to software engineering, which is more correct

I'm not exactly following through with the claim, can someone explain how the built-in classification would not necessitate more tokens used, or be much different from turning on reasoning? Not that I don't see the difference, I just doing see how OpenAI would do it well.

I more wonder if it's pure facts and evidence can work, or facts presented in a certain light can work? I guess asking how mush is it the data is presented that's doing more work than the data itself.

More surprised they don't mention RLHF once, as that's the main mechanism to the ability of AI chatbots.

Curious if or when we'll see the Qwen4 series, one thing I love with Qwen is it comes a much larger range of sizes so I can experiment which extremely small llms.

Archive Link: http://archive.today/IVreS

Well yes you won't have frontier capability but that doesn't mean you'd have nothing, I'm not sure what you have but I know there are tools that let you see what models (and their quant variants) you can safely run, I'd look into that first and see what options you have and what you're willing to delegate to a smaller model vs use opus for. Maybe opus to plan vs smaller models for focused implementation, or what works for you workflow and needs.

You might want to consider a local setup? Personally I do model + llama.cpp + Pi + tmux, that's as barebones as you can get and everything is great. I also use opencode for bigger task, I could probably hook that to a local model but I'm not sure (still new to this). But if you work with sensitive data you need a local setup purely.

> Liu also said Texas had established that TikTok's "Restricted Mode" did not work as advertised and exposed minors to content the company said would be filtered out.

I don't use tiktok, can someone explain what the restrict mode was advertised as vs does? If it's like any social media limiter it's perhaps a softer thing (time limit) than a hard thing (ie, designed to put the onus on the user).

Archive: http://archive.today/tnyRF

Could there come a limit to the G-cycle? Like either a) marginal gains slow/stall progress or b) more connectivity simply not being better? Curious to hear from folks in this field if this question has been raised.

Archive: http://archive.today/kt50V

Mate what is this even saying? Assuming we take the author put even 0.1% thinking into this, how would AI take over "Fuel and consumables"? All fuel (and lets even say energy) goes toward powering data centers, robots, and ai ventures? AI itself 'takes over' production, supply, or what? Also then this

> I asked Claude for a check-list of everything it needs to take over the world, destroy all the humans and somehow keep operating. No editing, no redacting, no censoring. I literally pasted its output between my header and footer. Claude wrote it in my voice but it's all Claude.

Okay so if the premise is what is needs vs not what it current can do, then 0% on fuel or energy makes no sense? Is Ai a plant that will discover photosynthesis?

Thanks, didn't realize the setup here was simpler than thought.

Off topic a bit but how do I design pages like this with github pages? I'm always very impressed by how far sites can design wise with pages but I'm still newish to it and not sure how to get there.

Isn't this a somewhat standard multi-model setup? there's nothing ground breaking here, just delegate claude to plan -> smaller model for implementation.

Archive link: http://archive.today/0Rxl7

> I am sick of underachieving beavers. Go us!

This really made laugh for some reason, just imagining a beaver typing away at HN specifically.