This one was quite an interesting story. Somehow even with their blank faces the AI was able to create a sense of trepidation or anxiety purely through body movements and I found that very impressive.
I find the AI voice painful to listen to, the script badly written, and it's full of nonsensical animations: https://youtu.be/LHhy4E9Hhmg?t=302
In fact the whole channel is just a poor clone of the channel Fern. Compare that video's thumbnail to one Fern made 6 months earlier: https://www.youtube.com/watch?v=_1bHK6uii7o, then take a look at the rest of their backlogs.
I did. The thumbnail may be the same but the story of the AI video is more interesting than Fern's which was just a brief overview of that particular case. I won't lie and say the AI video channels rip off human creators (Fern did a whole video about this too) but this particular video I linked was good.
Speed is actually the thing stopping me using local models more. Qwen 3.8 27b is surprisingly capable, but spends a lot of time/tokens brute forcing problems until it gets it right. The longer task times mean that to fully utilize my attention I need more tasks running concurrently, and the increased context switching just feels bad and leads to me making worse decisions.
I originally read your comment as quite gatekeep-y and elitist. The article explained some of the "theory" behind certain things around music in a way that made sense to me, yet here was a professional telling me it was bad because it was bad.
However I've realised that "Music Theory" is a strictly defined term. If someone made an article called "Intro to Algebraic Geometry", and it was actually about geometric algebra, it'd be really annoying, even if to a uninformed person the meaning behind those terms would seem interchangeable.
I think the way I've talked about incremental linking may have given a somewhat misleading impression. I'm not against incremental linking, and I'm not denying its possible usefulness. But especially when I was developing lld, I felt that we should focus first on speeding up full links.
Before I created lld, linking was much slower than it is today, and people somehow seemed to accept that as a given. People would often argue that since linking was slow, we needed to reduce the amount of linking work by implementing incremental linking. I thought that was too pessimistic. Why don't we just make the usual full link much faster, ideally almost as fast as a cp command, so that we don't need incremental linking nearly as much?
In other words, I wanted to solve the slow link problem head-on rather than work around linker slowness. And now we can link multi-gigabyte binaries in a second or two, which makes incremental linking much less urgent than it was ten years ago. That's pretty much what I wanted to achieve.
Am I satisfied with the speed? No. Could incremental linking speed it up even more? Maybe. Would it still be useful? Sure. It may well be worth doing. But people don't need it nearly as badly as they did ten years ago. I wanted to solve the larger problem first.
Yeah I recently tried the coding harness that's recommended here, Pi, in a bubble wrap sandbox and was horrified to learn that it spams multiple warnings at you if you don't give it write access to its own config/extension folder... Everyone else is rawdogging it I guess.
I think the best course is a docker container or a VM, i agree with the sentiment but trying to restrict the permissions of these things is fighting an uphill battle, it’s probably best to let them reign king in a disposable and isolated environment
You are horrified it needs access to its own stuff? I mean, any software that supports plugins needs access to them, no? How is that unreasonable? And with bwrap that’s an extra cli option.
