News for hackers. Stuff that matters.

ayolisup

Re:Infinite Tool Use on Sunday May 25, 2025 @10:40AM (#44088175)
A naive approach could be to create an outline, then have an LLM randomly sample a section, supply the surrounding context, rewrite that part, then repeat, ideally alongside human writing. Some sort of continuous revision cycle.
My bad for double posting, but they are probably referring to [this one](https://www.worldweatherattribution.org/climate-change-incre...), which says the exact opposite.
Unless we're talking about two different studies, saying you misinterpreted it is an understatement (https://www.worldweatherattribution.org/climate-change-incre...)
Re:Mixtral 8x22B on Wednesday April 17, 2024 @11:25AM (#40066032)
What's the best way to run this on my Macbook Pro?

I've tried LMStudio, but I'm not a fan of the interface compared to OpenAI's. The lack of automatic regeneration every time I edit my input, like on ChatGPT, is quite frustrating. I also gave Ollama a shot, but using the CLI is less convenient.

Ideally, I'd like something that allows me to edit my settings quite granularly, similar to what I can do in OpenLM, with the QoL from the hosted online platforms, particularly the ease of editing my prompts that I use extensively.

Too bad it is not available in .epub format, I'd love to read it on my ereader.
Re:Ads Don't Work That Way (2014) on Wednesday September 01, 2021 @08:24AM (#28378927)
In a very different style, I wonder what both of you think of this Superbowl ad: https://www.youtube.com/watch?v=mYsFUFgOEmM