Some of the Chinese labs with cheaper per token costs do support it, like say minimax: https://agent.minimax.io/max-claw

I haven't tried it to see if it's any good but it's $20/mo.

It's pretty trivial to do so on Arduino though.

  void setup() {
    pinMode(LED_BUILTIN, OUTPUT);
  }
  
  void loop() {
    digitalWrite(LED_BUILTIN, HIGH);  
    delay(1000);                     
    digitalWrite(LED_BUILTIN, LOW);   
    delay(1000);                      
  }

Well first you have to learn the Arduino programming language. And the stdlib.

They don't call it C++ because that sounds too difficult. But it's literally, not like a simplified subset that compiles into an IL using a formally proven tool, but as in literally compiled using GCC as, C++.

Calling it c++ might give the wrong impression to some people too, since it doesn't have the STL, rtti, or exceptions for boards like the Uno r3.

It is c++ though. Just limited in similar ways to the US air force's requirements for using the language.

it's literally the hello world of micros. get an arduino, plug it into the usb, install the ide, new -> example -> 01. Blink. Press Run. Cool you have now blunk a led. Now use AI to draw the rest of the owl.

It's easy once you've done it - but before you've done it (for me at least) it was much easier to just install a Linux on a Pi and run a bash script than to learn how to program an Arduino.

(Of course, there are those to whom an Arduino is an overpriced piece of junk and they don't understand how I can't solder a three cent chip myself.)

But let's be realistic - all of these things are like my Steam library - purchases made but never used (I have a drawer full of Pis and other SBCs, and Arduino dev kits, etc. Someday I'll have time time time!).

It's C++, and basically what Arduino gives you is

  int main() {
    setup();
    for(;;) loop();
  }

As well as a GUI to easily flash devices and view the output from the serial port, as well as import libraries that do all of the hard work like say making a serial port on any microcontroller pin or control external devices like light strips or displays.

I'd assume the average user on HN should be able to figure it out pretty easily.

Good thing LLMs exist now

> If your paycheck depended on following the instructions of an AI robot, the world might start to look pretty scary real soon.

That's already the case, minus AI, for gig workers. Their only agency is to accept or decline a ride/delivery, the rest is follow instructions.

You can run steam in big picture mode, and there are ways to add links to games from other game stores to steam such as https://github.com/PhilipK/BoilR

It's not automatic or perfect but it does work.

I'm aware, but that is indeed a great thing Steam offers. I think it's janky enough that if there's one way to out-steam Steam it might be making the broader PC gaming universe as plug-and-play into a console experience as possible.

I think this is still a place that steam does well - sure there is some jank, and definitely things left to be desired, but my two cents:

I fired up my…decade old? Steam Link the other day, got steam link clients on my phone, set up a couple steam accounts for my partner and kid, and turned on Wake on LAN on my desktop.

The streaming experience is _smooth_ whether it’s my phone or the TV, it Just Works and we can all play from our own libraries anywhere in the house.

I do wish Steam would clean up some of the pain points - in particular, not being able to switch users from a Steam Link feels like a huge oversight.

I haven’t touched much for gaming in MS’s world outside of just having windows by default, so no Xbox’s around since the 360, and I also really don’t know anyone who uses one. My friends are either PC or Steam, with a handful of us also on Switch. In my world and surrounding orbits, the Xbox is all but a meme at this point

Man I’ve only ever had a terrible experience with the Steam link. Idk how other people get such better results out of it

I definitely notice a difference in my desktop as the host (better everything, hardwired to the router) than my partner’s old HP, but they both do well enough.

It’s probably also important to note that the most we’re pushing it for is usually either Fallout 3 or StS2, neither of which need impeccable performance or low latency inputs.

Still, for our needs, it works great, and afaict is on par with both Nvidia and PS4/5’s remote streaming in terms of performance.

Agreed. I have a steam deck and my wife uses big picture mode on a PC. And both are full of jankiness that you don't get with something like the Switch. I actually bought a steam deck expecting a Switch-like experience, and man was I disappointed. Even the streaming is lacking compared to what Sony offers on the PS5.

I do wish Valve would spend some of their infinite money on sanding off the rough edges of Steam.

That's kind of how it feels though. I get the impression I'm micro managing various Claude code instances in multiple terminals.

In Claude code I believe it's /context and it'll give you a graphical representation of what's taking context space

You can also tell it the optimization to implement.

I asked Claude to find all the valid words on a Boggle board given a dictionary and it wrote a simple implementation that basically tried to search for every single word on the board. Telling it to prune the dictionary first by building a bit mask of the letters in each word and on the board and then checking if the word is even possible to have on the board gave something like a 600x speedup with just a simple prompt of what to do.

That does assume that one has an idea of how to optimize though and what are the bottlenecks.

Can we assume at this point if the problems are well known, the low hanging fruit has already been addressed? The Boggle example seems like a pretty basic optimization that anyone writing a Boggle-solver would do.

iOS is 19 years old, built on top of macOS, which is 24 years old, built on top of NeXTSTEP, which is 36 years old, built on top of BSD, which is 47 years old. We’re very far from greenfield.

What are the axes on the chart? Rpm?

Correct, RPM and Torque (%)

edit: images may be down for 5mins, migrating my blog to astro.

I agree, it'd actually be great if they did give maybe $5 or $10 worth of API tokens per month to max subscribers, since they're likely to be the most likely to actually build stuff that uses the Claude APIs.

I built a quick thing to download YouTube videos and transcribe them using with whisper, but it kind of feels clunky to summarize them using the claude CLI, even though that works.

just ran into this myself. I got Claude Code to build a tool that calls Claude for <stuff>. Now I have to create a console account and do the API thing and it sucks balls.

> I'm not sure what the best use of $1k is from a health standpoint is, just noting that it's good to have a comparator.

Spending 1k on a gym membership and more fresh vegetables would be a pretty high return on investment, if one isn't in shape and eating healthy already.