Jyaif

I one-shotted non trivial software from OpenGL to Metal with a cheap (=non state of the art) LLM. That was 6 months ago.

Anything in Unreal Engine that you think Fable wouldn't be able to adapt on its own to a different graphics API?

I don't think the Game Porting Toolkit is useful these days: LLMs one-shot ports from one graphics API to another.

Just like programming languages, graphical API choice is irrelevant now.

The title sounds like a line from a KRAZAM video ( e.g. https://www.youtube.com/watch?v=eDr6_cMtfdA )

For one, as of today SOTA LLMs sometimes take the wrong decisions

If you build stuff with AI it's different. It's very tempting to defer many (too many?) decisions to AI.

he could have easily achieved a solid living via crowdfunding, even for San Francisco standards.

That sounds completely surreal. Is Bun really used that much?

Nobody knows if we are going to "just" be riding bikes for a long time. To give time for society to adapt I hope it's the case, but we really have no idea.

I tell folks there's a chance GTA6 will be ported to PC before it's officially released to PC.

Ever since the android debacle with icons having shadows going in different directions or length I've been thinking that icons should be 3D models (with restrictions to make them fast to render and/or fast to bake into flat images).

That would be a marvelous way to make icons unified and a differentiating move for Apple.

What's the difference between disabling faulty cores and disabling the parts of the wafer that have defects?

Broadcom will let the entire industry leverage the decade of research done for TPUs.

The AI business of Nvidia is cooked.

Possibly stupid question: if we are OK with using Arc everywhere in the UI (UIKit style), does that help?

Dell is screwed by the software and never made the investment in a good touchpad.

I’ve had feedback this name is terrible

GridLion is an excellent name

How do you envision the correctness of these solutions being judged?

By LLMs. I think it's possible for agents to infer whether the user was satisfied or not, at least with my usage pattern. For example if I end the discussion it's a good sign. If I ask follow up question that look like workarounds, it's a bad sign :-)

You could also simply prompt the users whether they were satisfied with the answer they received, possibly incentivizing them with StackOverflow-style gamification.

We unironically need an StackOverflow for LLMs.

LLMs would post solutions to the issues that they've discovered after doing a lot of research.

Unfortunately the LLMs are concentrated into few providers (OpenAI, Anthropic, Google) so there's a chance they each end up doing their own private (and closed) StackOverflows. By leveraging their private StackOverflows, their LLMs will be able to short-circuit complex reasoning, saving tokens, time, and money.

What are the chances it goes through?

A sign that you are paying for the logo is that it's present 8 times freaking times on the body.

And just to be sure you get it, "Ferrari" is also spelled out.

it could replace a bunch of $100k+/year workers.

I love AI, but it's possible that we are in an temporary golden age of software development because of 3 things:

1. The software is simple because lowly humans wrote them and debugged them and maintained them.

2. The humans are competent in software engineering.

3. All of a sudden we now have help from AI.

Point 3. is here to stay, but 1. and 2. could disappear.

Perhaps additional financial incentives for people to not spend hours of their day in cars is a good thing?

Eventually all the domain name purchasing will be done by agents. (Easiest prediction ever)

How big is the state that you want to rollback?

And you can tell that TI pretty clearly copied the NumWorks calculator.

Those transparent bezel look incredibly good.

Machines were roughly doubling in performance every year back in 2000.

Nowadays they are doubling in performance every... 5 years?

not much preventing your game engine from having a pluggable system where you could have the various different patches of the game engine ship with every subsequent release of the game

Starcraft 2 does that. It's still quite an achievement.

Folks that do this work for "free" do it because they enjoy it.

And a small observation: if you require money to do something, you usually have no chance of being as good as the folks that do it for the pleasure.

Unless you need some windows-only software, using windows at this point is masochism. I was never a fan of Linux, but the Microsoft driven enshitification is so strong that Linux is now a better option. To win, all Linux had to do is stand still, and that's exactly what it did! Ubuntu in 2026 is pretty much the same as Ubuntu from 2006.

Despite all the investments, the industry can't keep up with the demand for AI. And that's when the industry isn't even offering state of the art AI.