c1b

You can enable it in settings; works on my older iPhone.

Yes it just collapses eventually — never stabilizes. The training process is flawed, I suspect it has to do with the fact that some weights blow up over time, you can see in “weights” tab.

But at around 4K avg score you should see it solve the env almost every time.

Just a demo :) optimized for speed over stability.

Reward structure: Step: -1 Dot: +100 Win: +1000 so ~4k is max theoretical score on 6x6; the model will eventually break if you keep training long enough.

daniel youre a legend, thanks for all you do!

one question, I see perf comparisons here are done on an L4, but isn't this SKU very rare? Im used to T4 at that tier

So o1 pro is CoT RL and o3 adds search?

How does o3 know when to stop reasoning?

does this also already exist on llvm toolchain?

Wow, you're the most passionate hater of ARC that I've seen. Your negativity seems laughably overblown to me.

Are there benchmarks that you prefer?

Hi Francois, I'm a huge fan of your work!

In projecting ARC challenge progress with a naive regression from the latest cycle of improvement (from 34% to 54%), it seems that a plausible estimate as to when the 85% target will be reached is sometime between late 2025 & mid 2026.

Supposing ARC challenge target is reached in the coming years, does this update your model of 'AI risk'? // Would this cause you to consider your article on 'The implausibility of intelligence explosion' to be outdated?

CSGO model is only 1.5 gb & training took 12 days on a 4090

https://github.com/eloialonso/diamond/tree/csgo?tab=readme-o...

What is this for exactly? Go should be used serverside, and Qt looks like its for UIs on embedded devices?

Its simple -- you see a justine.lol url, you click immediately

> The difference is that the A6000 absolutely smokes the Mac.

Memory Bandwidth : Mac Studio wins (about the same @ ~800)

VRAM : Mac Studio wins (4x more)

TFLOPs: A6000 wins (32 vs 38)

I cannot comment specifically on CHEETAS, but what I can say is that USG developing in house software solutions almost always produces a disastrous product that goes over budget and has extreme maintenance overhead.

To see why, you can simply ask yourself: do you think that the unelected officials overseeing government agencies that embark on enterprise software development projects have sufficient expertise and enterprise software project management experience to be able to do this well?

Furthermore, do you think that the quality of engineers that the NHS or DoD can attract with less than half of the compensation of an actual software company stands a chance at developing something good in house?

It’s unfortunately almost impossible for these projects to go right.

It varies by agency — either something built in house (very bad) or built by a company that knows how to acquire government contracts, of which there are few - the set of which frankly always has worse tech than Palantir. If product efficacy is not absolutely critical, the acquisition process will be driven by nepotism or other forms of corruption.

As an example for the second case in DoD space, there’s Advana.

Let me rephrase: I am extremely familiar with the USG data management tech landscape.

As someone familiar with the USG data management tech landscape — it’s probably because it’s by far the best product with no remotely close second.

“As if LLMs are doing something creative and aren’t just algorithms”

You have no idea what you’re talking about huh?

Its AR

So you just gave three examples off the top of your head but you need to make sure he picked the right one..?

I somewhat follow, but it seems shares have privileges that cannot be synthesized in the same way that dividends and value can. For example, if the firm votes for a new CEO, these shares should have voting power, but B cannot fulfill this obligation to A, so how can these shares be resold to multiple buyers?

This is not entirely accurate. It is the same position as borrowing some amount of money to buy the stock. If I buy a put and call and the price at expiry is exactly that strike I am guaranteed to lose money.

Both AirPods that have been released have already been wayyyyy better than every “established” earbud product in their price category. Don’t see why you would assume that AirPods Max would all of a sudden be worse.

heard of gold?

human invention? heard of rocks?

sounds like you don't know any Uber/Lyft drivers

You're thinking about this wrong. P/E 40 is comparable to an interest rate of 2%. Would you rather take 0% from bonds?

lol. this is insane. he's doing his job and asking a question.

Lets say he decides to start being more diligent and taking the initiative to do as much work as is possible. His company is the only entity that benefits from this arrangement, and the benefit is marginal at best. Ultimately, this literally provides the resources for the company to pay the salaries of more useless workers and perpetuates the issue this post is trying to address.

In which situations is React unsuitable? I learned web development starting with React and have been using it for everything since.

Yes this example is very pertinent to Amazons profit strategy thank you for sharing.