I am not a programmer, but on 2 occasions I was able to improperly fix (1 argument in 1 line stuff) very small bugs without really understanding how. I've also made a number converter (dec-bin-hex) at least twice. I know those aren't a lot but it's weird that it happened twice twice.
I'd say there's an issue here with language design having major tradeoffs, but maybe it's just a paradox*? Though I have found a language I like (even though I'm not learning it because other issues), so I know it's not impossible at least.
*= Like the people who could make something with less tradeoffs don't have the need/desire to do that, they just use the existing stuff. Though that is much more fitting for visual programming.
I am researching doing the same, but know nothing about running my own yet. Did you train your llm for programming in any way, or just download and run an open source one? If so which model etc do you use?
Lot’s of technical details, but essentially the llamafile is a engine + model + web ui, in a single executable file. You just download it and run it and stuff happens.
Run an open source one. Training requires lots of knowledge and even more hardware resources/time. Fine tuned models are available for free online, there is not much use in training it yourself.
I recommend llavafiles, as this is the easiest option to run. The GitHub has all the stuff you need in the “quick start” section.
Though the default is a bit restricted on windows. Since the llavafiles are bundling the LLM weights with the executable and Windows has a 4GB limit on executables you’re restricted to very small models. Workarounds are available though!
Im gonna give llamafile a go! I want to try to run it at least once with a different set of weights just to see it work and also see different weights handle the same inputs.
The reason I am asking about training is because of my work where fine tuning our own is going to come knocking soon, so I want to stay a bit ahead of the curve. Even though it already feels like I am late to the party.
The only place I’ve seen ruby used extensively is in environments with a lot of regular expressions and string manipulation. Still not entirely sure why I’ve only seen it used there. The regex tools in ruby are nice but they aren’t nice enough to justify a language switch in my opinion…
It’s the part of ruby that replaced perl. For whatever eldritch horror perl was it was very, very good at doing text manipulation, and IME the only language to really match that experience was ruby.
this is literally how we work now in construction. because everything is digital people think that this is an acceptable approach. all my costing files are purposefully extremely dynamic.
you want to add another floor? no problem.
you want to change some floors from 3 bedroom to 2 bedroom? no problem.
you want to remove a parking floor and have outside parking? no problem. you don’t want to have low hanging beams? no problem.
and so on and so on…
i know i should not be working like this, but sometimes i have to.
programmer_humor
Top
This magazine is from a federated server and may be incomplete. Browse more on the original instance.