I know that LLM and AI are kind of dirty words in the app dev community and I get the reasons why. Even if you just keep living your life, folks like Dropbox (https://boingboing.net/2023/12/14/dropbox-is-sharing-users-files-with-openai-heres-how-to-opt-out.html) and GitHub are using your data to train their LLMs. I think that there is an opportunity in ethically sourced AI, though. Even if you disagree with that statement, there is a "know your enemy" argument.
That's the reason why I have been trying to learn this shit, lately. ...
... I have tried running #Llama 2 (https://ai.meta.com/llama/) locally and I haven't been able to figure it out yet but it is the reason why I decided to replace my 2017 MBP with a 2021 MBP (with double the RAM and an M1 Pro instead of an i7).
I did have some success with #llamafile (https://github.com/Mozilla-Ocho/llamafile), though. Mozilla released something that lets you package a set of weights as a single multi-gigabyte executable that can run on macOS, Windows, Linux, FreeBSD, OpenBSD, or NetBSD. ...
On Monday, Mistral AI announced a new AI language model called Mixtral 8x7B, a "mixture of experts" (MoE) model with open weights that reportedly truly matches OpenAI's GPT-3.5 in performance—an achievement that has been claimed by others in the past but is being taken seriously by AI heavyweights such as OpenAI's Andrej...
Other than (maybe) describing images, what has anyone found #Llama#LLM useful for?
I'm trying it occasionally on different things but mostly it isn't up to the task. For those simpler questions it can answer it is way slower than doing a web search. 🤷♂️
@jsbarretto that's not something I have much use for, but I'm also wondering if they (though I was really taking about #Llama) produce plausible summaries or good summaries.
Having forgotten everything I ever knew about #Perl I'm trying to extend a script I wrote years ago and am almost at the point of asking #Llama#LLM for help.
I mean, assigning a string with an embedded variable really should not be hard 🤷♂️
All in an effort to make my faithful old #ftpdns use SSH and SCP instead of FTP, which stops working every time someone in a datacentre sucks their teeth.
User: make a list of things I might find you useful for
Llama: Sure, I'd be happy to help you with that. Please provide me with a list of things or tasks you would like assistance with and we can work together on them.
It took nearly a minute of hammering my eight CPU cores to come up with that. 🤷♂️
I think we're safe from #AGI for the foreseeable. Don't listen to twerps like #SamAltman who is just shilling.
Serious question. It's interesting to play with but I haven't found anything I'd use it for yet. The only thing it seems it may be good at is summarising a news page and articles filtered by subject - though I'm not sure that's really useful to me.
Well, I'm sure an NVDA addon with this will be here soon. Just amazing how far things have come. I mean, I hope there's a Windows version of the Llava part of this anyway.
llamafile is the new best way to run a LLM on your own computer:
The wife and I had a good laugh today while I was experimenting with #LLM's. Feeding #Claude a complex prompt that analyzes forum posts, it decided that her career in pharmacy is a crime. 🤣
That said #Claude is still really good, I just need to find the right approach to make it act consistently. I doubt my problem is math, but it is mixing up numbers (0 is 10 is 0 is...). 🤔
I'd assume GPT-4 will work better, but the point is I'm trying to do stuff without OpenAI.
Right now I'm exploring if my idea is viable (it looks promisimg), then I'll move on to recreating it on #Llama and fine tuning.
Mise à jour par rapport à mes vidéos précédentes du printemps.
Petit essai en vidéo de #Openchat3.5, un nouveau modèle de #LLM libre utilisable avec #llama.cpp, et qui prétend être comparable à GPT 3.5 Turbo, l'avant-dernier modèle d'OpenAI.
La vidéo est aussi faite pour montrer ce que ça donne en rapidité sur un processeur "normal", sans usage du GPU.
Welp, here we go. Be My Eyes is so great, people are just... Calling their projects Be My Eyes web apps now. Cause it's 2023 and here we are. No, I haven't tried this thing. I hope it's worth the absolute shitstorm of a hype train this will cause in the blind community once people get to looking at it.
Meta's #Llama 2 license has an unusual clause whereby they withdraw your right to use the model if you allege #Meta has breached your own IP rights by training their stuff on your intellectual property. #copyright#genai#LLama2
Climate change is an immediate threat to the majority of the world's population.
We need a local, regional, state, national, and international "moon shot" type of concentration of effort using available resources while developing and advancing new science and technologies to counteract the damage humans have caused.
Without this type of all-out, universal cooperation, human civilization, and perhaps humanity itself, are in imminent danger of extinction.
Everybody’s talking about Mistral, an upstart French challenger to OpenAI (arstechnica.com)
On Monday, Mistral AI announced a new AI language model called Mixtral 8x7B, a "mixture of experts" (MoE) model with open weights that reportedly truly matches OpenAI's GPT-3.5 in performance—an achievement that has been claimed by others in the past but is being taken seriously by AI heavyweights such as OpenAI's Andrej...