People have been trying to ascribe consciousness to machines since the 1800s and the advent of ‘calculation engines.’ Robots and Golems were physical manifestations. Can go even earlier, but those were speculative fiction.
Scrape the surface of anyone pushing ‘machines are like humans’ and it always ends up being a money-raising grift. Good luck with that.
The reason computers originally became popular in cars was to help with fuel efficiency. So it could figure out the proper fuel-to-air mixture and engine timing on-the-fly. Everything else could be done through physical wires, switches, and electric servos.
The problem is manufacturing and repairing all those wires, switches, and servos becomes cumbersome. So manufacturers moved to modular pods that could be plugged together via bus harnesses. That way, you can pop out a malfunctioning box and be back up, instead of requiring the corner mechanic to become an automotive engineer.
The problems started when each of those boxes were made to be closed and proprietary, requiring custom integration and tools. The vehicle makers became systems integrators, wanting to lock out competitors by forcing all repairs to go through their dealer network and using their expensive parts.
If someone figures out how to get all the benefits of modularization without all the negatives of vendor lock-in, and throw out the pointless telemetry collection, that would be a great place to start.
People wanting to also center it vertically is what broke the web.
New AWS us-southeast data center just went online.
Simon may want to randomize his Pelican/Bicycle test.
There is a long tradition in tech of firms tweaking their outputs to get higher scores on well-known tests. The ultimate example is VW Dieselgate.
But in AI, it’s easy to game benchmarks, by adding the best answers to the training set for the next version.
Nothing a little bodge-wiring and a Pi compute-module can’t fix.
This feels like it needs a ‘Hunger Games’ add-on.
It’s Texas.
Yes, but which Instagram/Snapchat filters will they have available in space?
The Macbook has 128GB RAM so it can run some beefy local models. The Qwen family of models are pretty good, but I use LMStudio to switch around. For experimenting, kt’s good to have a large SSD drive. None of the local models are as good or fast as the big/centralized ones, but the code stays on the machine, and you don’t have to pay monthly or token fees.
For serious dev work, you’ll still want at least one of the big ones, in case the local one gets into a loop.
The Macbook has slightly better speakers, but I mainly use bluetooth headphones to listen to music or videos.
I used to develop iOS apps professionally. For a solid 5-6 years, used nothing more than a Macbook Air. It was light, easy to take to a coffee shop, and I could run VMware or Parallels on it for Linux and Windows development. Worked great, especially if you could connect it to an external monitor so each window could be its own OS. The two things you can’t change are RAM and built-in SSD storage. I’d take those higher if you can afford it.
My current machine is a Macbook Pro, but that’s because I run local LLMs and databases on it. If I was only doing mobile development, it would be way overkill. Not sure if the Neos have enough power to run Xcode.
Giving all those people with stupid, penis-oriented, middle-school email acoounts a second chance.
It’s not just the compiler. It’s all the libraries.
Was jokingly going to suggest a WASM version. But then: https://github.com/ffmpegwasm/ffmpeg.wasm
They’re trying to low-key, sneak in VBscript and XAML.