Suche
Beiträge, die mit LLM getaggt sind
#github #mastadon #microsoft #siliconvalley #foia #journalism #nyc #boston #nft #digitalart #google #llm #llama #meta #gemini #charity # #philanthropy #activism #election #electionday #huggingface #perchance #chatgpt
https://sites.google.com/view/dan-tech-blog
@altbot
#LLM #tech #blog #ai #cybersecurity #phishing #perplexity #perplexityai
#translation #LLM #AI #writing
One area where language models might actually be good is emulating a type system for dynamic languages.
Given how good these things are at figuring out general shape of the code, I suspect they could fairly accurately tell you argument and return types for functions. And you could probably get away with a pretty small model if it only targets a specific language.
I'm kind of surprised nobody's tried doing this yet.
#technology #programming #machinelearning #llm
Yogthos (@yogthos@social.marxist.network)
84 Posts, 1.3K Following, 217 Followers · A sentience trapped in a prison of meat. Made in USSR. Capitalismus delendum est! ☭Yuggoth
Given how good these things are at figuring out general shape of the code, I suspect they could fairly accurately tell you argument and return types for functions. And you could probably get away with a pretty small model if it only targets a specific language.
I'm kind of surprised nobody's tried doing this yet.
#technology #programming #machinelearning #llm
https://www.sciencedirect.com/science/article/abs/pii/S0169260724003067
#AI #LLM #PeerReview
https://www.thelancet.com/journals/laninf/article/PIIS1473-3099(24)00160-9/fulltext
1. In an experimental peer review report, #ChatGPT "made up statistical feedback and non-existent references."
2. "Peer review is confidential, and privacy and proprietary rights cannot be guaranteed if reviewers upload parts of an article or their report to an #LLM."
"Several publishers…have barred researchers from uploading manuscripts…[to] #AI platforms to produce #PeerReview reports, over fears that the work might be fed back into an #LLM’s training data set [&] breach contractual terms to keep work confidential…[But with] privately hosted [and #OpenSource] LLMs…one can be confident that data are not fed back to the firms that host LLMs in the cloud."
https://www.nature.com/articles/d41586-023-03144-w
How ChatGPT and other AI tools could disrupt scientific publishing
A world of AI-assisted writing and reviewing might transform the nature of the scientific paper.Conroy, Gemma
Some tools already cite sources. But when will tools promise that their citations are real and relevant — and deliver on that promise?
It has a chatGPT kind of thing, but when the #LLM doesn't know, it says it doesn't know, and when it claims to know, it shows where it got the information. Its answers are not always correct, but by looking at its sources, that's possible to see.
https://search.brave.com
#AI
All the talk about it being so new and different just seem like deliberate obfuscation as a stalling tactic against regulation.
#GenerativeAI #LLM #AI #StochasticParrots
"Follow This One Trick to Write Great Headlines"¹
https://sadlynothavocdinosaur.com/posts/headlines/
I figured generating a headline is kind of the apotheosis of this week's prompts. I mean, ideally, it feels like a headline is a distillation of a text's essence.
____
¹ Day 9 of my series on prompt engineering. https://sadlynothavocdinosaur.com/posts/50-days-of-lit-prompts/
#AI #LLM #promptEngineering #GPT
50 Days of LIT Prompts | Sadly Not, Havoc Dinosaur
Every weekday for the next 10 weeks, I'll update this page with new prompt patterns and invite folks to play with them inside LIT Prompts.sadlynothavocdinosaur.com
https://sadlynothavocdinosaur.com/posts/email-to-do/
____
¹ Day 8 of my series on prompt engineering. https://sadlynothavocdinosaur.com/posts/50-days-of-lit-prompts/
#AI #promptPatterns #LLM #promptEngineering #GPT
50 Days of LIT Prompts | Sadly Not, Havoc Dinosaur
Every weekday for the next 10 weeks, I'll update this page with new prompt patterns and invite folks to play with them inside LIT Prompts.sadlynothavocdinosaur.com
You Can't Be Neutral on a Moving Train: https://sadlynothavocdinosaur.com/posts/define-words-in-context/
"...AI art doesn't copy human artists the way you think it does & that queasy feeling it gives you isn't about copyright. It's antitrust and labor."
We also revisit Tuesday's prompt, adding context and improving its performance.
____
¹ Day 4 of my series on prompt engineering. https://sadlynothavocdinosaur.com/posts/50-days-of-lit-prompts/
#AI #promptPatterns
#LLM #promptEngineering
#GPT
50 Days of LIT Prompts | Sadly Not, Havoc Dinosaur
Every weekday for the next 10 weeks, I'll update this page with new prompt patterns and invite folks to play with them inside LIT Prompts.sadlynothavocdinosaur.com
I'm Sorry, Dave Can't Do That: [Have AI] Use the text of an email to draft a polite reply declining any request(s)¹
https://sadlynothavocdinosaur.com/posts/decline-requests/
"Sometimes you just need to solve the blank page problem."
____
¹ Day 3 of my series on prompt engineering. https://sadlynothavocdinosaur.com/posts/50-days-of-lit-prompts/
#AI #promptPatterns #LLM #promptEngineering #GPT #EmailEtiquette
50 Days of LIT Prompts | Sadly Not, Havoc Dinosaur
Every weekday for the next 10 weeks, I'll update this page with new prompt patterns and invite folks to play with them inside LIT Prompts.sadlynothavocdinosaur.com
https://sadlynothavocdinosaur.com/posts/define-words/
What if I you could select a word or phrase, click a button, and get a definition, be it for a word, idiom, or initialism without leaving the page you're on? Well, I'm happy to say today's prompt template does just that.
It also starts us down the path of understanding how a neural net works!
____
¹ Day 2 of my series on prompt engineering. https://sadlynothavocdinosaur.com/posts/50-days-of-lit-prompts/
#AI #promptPatterns #LLM #promptEngineering #corpusLinguistics
50 Days of LIT Prompts | Sadly Not, Havoc Dinosaur
Every weekday for the next 10 weeks, I'll update this page with new prompt patterns and invite folks to play with them inside LIT Prompts.sadlynothavocdinosaur.com
https://sadlynothavocdinosaur.com/posts/summarize-and-question/
"...everyone's been handed a telescope [LLMs], and they keep looking through the wrong end... Instead of writing prompts with 5 words and expecting 500, more folks should be providing 500 and asking for 5."
____
¹ The first in my 50-day series on large language models. See https://sadlynothavocdinosaur.com/posts/50-days-of-lit-prompts
#AI #promptPatterns #LLM #promptEngineering
50 Days of LIT Prompts | Sadly Not, Havoc Dinosaur
Every weekday for the next 10 weeks, I'll update this page with new prompt patterns and invite folks to play with them inside LIT Prompts.sadlynothavocdinosaur.com
This one is particular nice. GPT4All with hermes model. Snoozy came in second over multiple tasks so far. Running on the smallest M1 Mac.
#gpt4all #llm #packrafting
https://github.com/rupeshs/alpaca.cpp
It maxes out all of my cores when running and is even then pretty slow 🙃 The english text produced is fine, but the factual content is pretty bad. #llm #gpt
GitHub - rupeshs/alpaca.cpp: Locally run an Instruction-Tuned Chat-Style LLM (Android/Linux/Windows/Mac)
Locally run an Instruction-Tuned Chat-Style LLM (Android/Linux/Windows/Mac) - GitHub - rupeshs/alpaca.cpp: Locally run an Instruction-Tuned Chat-Style LLM (Android/Linux/Windows/Mac)GitHub