MattRix

Why not? Not everything has to be SOTA to be interesting.

I think Anthropic did the mythos announcement to undercut OpenAI’s upcoming next model announcement, not Meta’s.

Where is the astroturfing? From what I can tell it’s maybe the fastest growing product/company ever. Anthropic’s products have completely changed how software development gets done across the entire industry, especially in the past four months. The level of hype seems entirely justified to me (and I say this as an OpenAI Codex user).

This is what happens when you have growth that is exponential instead of linear!

yeesh yep, though it's more Pandora's Box than a can of worms, since it can't exactly be closed once it's opened

I don't see why not, especially with computer use and vision capabilities. Are you talking about their lack of physical embodiment? AGI is about cognitive ability, not physical. Think of someone like Stephen Hawking, an example of having extraordinary general intelligence despite severe physical limitations.

The thing is that the current models can ALREADY replicate most software-based products and services on the market. The open source models are not far behind. At a certain point I'm not sure it matters if the frontier models can do faster and better. I see how they're useful for really complex and cutting edge use cases, but that's not what most people are using them for.

They aren’t stopping anyone from using claude -p, they are just charging for that usage.

hah that’s a great way to explain it

This is not lying, that is just what run rate revenue means! It makes sense to use as a metric when a company’s user base is growing as fast as Anthropic’s is.

Brandon Sanderson recently did a talk about something similar: https://youtu.be/mb3uK-_QkOo

I think this is because when you shrink it down, the model ends up space constrained and each “neuron” ends up having to do multiple duties. It can stil be tuned to perform well at specific tasks, but no longer generalizes as well. It’s somewhat unintuitive but models that are larger are often simpler than smaller ones for this same reason.

It’s not hypocritical at all. You can be a fan of a technology and still acknowledge its downsides. Every technology has places it is useful and places it is harmful.

what’s to keep people from selling or giving away those id tags? seems like a nefarious entity could buy them in bulk

Fun fact: because WFC is graph-based, you can do stuff like creating a graph where it uses time as a dimension, so you can create animations that “wrap” in time.

In this rabbit example I made 8 years ago, the WFC solver ensures that the animation must loop, which means you will always end up with an equal number of births and deaths.

https://xcancel.com/MattRix/status/979020989181890560

Nope. As someone who has tried to get tickets, most of the matches are sold out, and even the least desirable matches are quite expensive.

Yes, the LLM writes the specs. In fact that LLM writes everything, and then the humans only flag anything they want changed, other than that it’s completely automated.

Imagine you were working with a very talented software shop. You might tell them your preferences sometimes and some things you want changed, but otherwise they mostly just build the right things the right way. And unlike a real software shop, the LLM system can implement changes incredibly fast.

Yup. This is exactly what is going to happen. It’s strange that so many people here can’t seem to extrapolate from the current state of things. It’s inevitable.

Did I say you stated otherwise?

I’d encourage you to read this post: https://factory.strongdm.ai

It hit the front page here a few weeks ago, but I don’t think most people took it seriously and got hung up on the $1000/day in tokens part.

I am convinced that approach is the future of nearly all software development. It’s basically about how if you’re willing to spend enough tokens, these current models can already complete any software task. With the right framework in place, you don’t need to think about the code at all, only the results.

I really don’t like that the industry is heading this way, but the more I consider that approach, the more I’m convinced it is inevitable.

The humans working there do. To state otherwise is to absolve those humans of any responsibility.

This is a really weird response man. No need to get so judgy and personal.

Besides, as far as I can tell what they said is true. The users are losing access to Antigravity, not to their entire Google accounts. So you’re getting mad at this guy just for stating facts.

The thing is that this is genuinely useful to Googlers as well. If they’re internally dogfooding their tools and models for coding, it seems likely that things will improve.

This is what people already do with “ralph” loops using the top coding models. It’s slow relative to this, but still very fast compared to hand-coding.

Anyone who has used OpenClaw knows this is VERY plausible. I don’t know why someone would go through all the effort to fake it. Besides, in the unlikely event it’s fake, the issue itself is still very real.

I mean, sure, why not?

I’ve been using it a dozen times a day for the past 14 years with very few issues. Certainly not enough issues that I would ever want to go back to adding things like alarms and reminders and events by hand.

This is an absurd take. Of course tons of people use Siri. It’s by far the fastest way to create alarms, reminders, and events. If Apple got rid of it, I would feel like a cave man, having to unlock my phone and navigate multiple screens just to do basic tasks. I’d immediately switch to Android.

If you don’t think the quality has improved then you haven’t actually been trying it. Any programmer who knows what they’re doing can immediately tell models like Opus 4.6 and Codex 5.3 are much better than models from a year ago. All the objective metrics (benchmarks etc) agree as well.

It’s not challenging at all. You leave the buffer. If someone sees the gap and merges into it, that’s fine! You always maintain the buffer.

It’s not hard to do. It’s only frustrating if you let it be. It really barely slows you down at all.