8,476 karma · joined September 7, 2018
This looks like a hack just for the main file, it would have been good if these functions can be called from other files.
- doesTerm.everything run inside tmux with automatic window resizing? I guess not, but it would be cool
GeoHot didn't want to make it only FlashAttention specific, he worked on FlashAttenrion being automatically generated by the optimizer. It's going well
The only problem I have is that I bought a new beelink Pro9, put Omarchy on it and Hyperland locks up every day, and I don't know if it’s only me or not.
Tapping the prompts in is the easy part, but async model is different to work with, I feel more like a manager, not a co-developer.
It's interesting that most people seem to prefer local code, I love that it allows me to code from my mobile phone while on the road.
For Turbo mode I understand the need for paying but the main poing of running a local model with web search is browsing from my computer without using any LLM provider. Also I want to get rid of the latency to US servers from Europe.
If ollama can't do it, maybe a fork.
Everybody who really wants knows which country benefited the most from the Nordstream pipeline being destroyed.
Of course I agree with all the other points that you have made, but at least this part wasn't just Brussels administration.
An example is the first Microsoft bot that started to go extreme rightwing when people realized how to make it go that direction. Grok had a similar issue recently.
Google had racial issues with its image generation (and earlier with image detection). Again something that people don't forget.
Also an OpenAI 4o release was encouraging stupid things to people when they asked stupid questions and they just had to roll it back recently.
Of course I'm not saying that that's the real reason (somehow they never say that the problem is with performance for not releasing stuff), but safety matters with consumer products.
What works for me is that after having lots of passing tests, I start refactoring the tests to get closer to property testing: basically prove that the code works by allowing it to go through complex scenarios and check that the state is good in every step instead of just testing lots of independent cases. The better the test is, the harder LLMs are able to cheat.
At this point it's much more interesting how well the Robotaxi is doing. It's still not driving like Waymo (I didn't like how it is desregarding the rules), but in a few years if it is able to scale up, it will scale much much faster and cheaper.
I just don't understand the reason, why any Tesla shareholder wouldn't like the 400% return in 5 years, just because BYD had even better return and forced some margin compression on Tesla.
Stop caring. You can contribute even more somewhere else later. Do your job, exactly 8 hours, focus on work-life balance, but leave quietly and professionally.
It's much better to ask the specific queries that you yourself would do with sed and treat the models as smarter sed (or ask them to generate the sed statements themselves)
Now he's making a for profit company and there's already MAX and MAX Enterprise stuff to not trust that the open source part would be competitive with already great inferencing frameworks for example.