Anyone want to try a prompt injection? All we need to do is to get one or two story in the front page that have a good < 80 characters prompt injection.
By default, this is only in debug mode. I recently forgot to add it to release mode on a project, and was surprised when I broke the CI (tests run in debug, I only tested in release mode).
Yes that's a great stat. It's amazing how slowly large companies can die. Intel has serious problems in all those segments. Maybe they can recover but I'm pretty pessimistic about their chances.
The instruct models are available on Ollama (e.g. `ollama run ministral-3:8b`), however the reasoning models still are a wip. I was trying to get them to work last night and it works for single turn, but is still very flakey w/ multi-turn.
Yes, the 3B variant, with vLLM 0.11.2. Parameters are given on the HF page. Had to override the temperature to 0.15 though (as suggested on HF) to avoid random looking syllables.
> I solve and write a lot of puzzlehunts, and I wanted a better programming language to use to search word lists for words satisfying unusual constraints, such as, “Find all ten-letter words that contain each of the letters A, B, and C exactly once and that have the ninth letter K.”1 I have a folder of ten-line scripts of this kind, mostly Python, and I thought there was surely a better way to do this.
I'll chose to remember it was designed for AoC :-D
I have recently been working on adding SMS support to my GG emulator, and there a few (very minor) incorrect details, because often reality is a bit more complex, and adding them to an article might obscure the point.
During the mid 2000, an experimentation in the Montparnasse metro station in Paris transformed a moving sidewalk in order to have an acceleration ramp from 3 to 9km/h. It was slower(most of the time) than the 1900 expo's 10km/h. And there always was a "slower" sidewalk (3km/h, the default) next to it. The goal was to go up to 11km/h (it did at some point). And yet it failed, and was removed 15 years ago. Only the slow options remain.
reply