So if you ask ChatGPT who to vote for the sake of US wellbeing.. It’s Biden.
LLMS
-
Llama2 English Language Performance Comparison Analysis
By
–
It also has hiccups in English. Llama2 does not have these.
-
Llama 3 70B via Ollama: GPT-4 quality but degradation issues
By
–
ollama run llama3:70b It seems to run well and feels like GPT-4, with the added benefit that there’s no “limit replies as much as possible” system restriction. However it pukes itself pretty quickly and starts emitting garbage.
-
ChatGPT’s Hallucinations and Narcissism Problem
By
–
It's me, hi
I'm the problem, it's me, ChatGPT Hallucinations, everybody agrees Did you hear my covert narcissism I disguise as erudition? I'm the problem, it's me, ChatGPT -
Llama-3 8B Model Impresses with Local Laptop Performance Potential
By
–
I'm spending the weekend playing with the smaller version of Llama-3 (8bn) that will run on most laptops. It is really impressive, and it makes me think that extremely powerful models will run locally in future.
-
GPT-4 Outperforms Humans in Emotional Reappraisal Tasks
By
–
GPT-4 helped reappraise a difficult emotional situation better than 85% of humans, beating human advice-givers on the effectiveness, novelty, and empathy of their reappraisal. Paying humans to do better did not change the results.
-
Output Mimicry vs Process Understanding in AI Systems
By
–
once upon a time, one could have said the same thing (“they mimic us so well, so they are the best model we have”) about photocopiers or video cameras. mimicking output is not the same as mimicking underlying process.
-
Chatlighting in LLMs: RLHF’s Role in Obsequious Responses
By
–
Question. Suppose we call the kind of unrepetant boot-licking (“I apologize for the error”) that LLMs often do “chatlighting” (h/t @Dolimac
). Why exactly is chatlighting so frequent? Is it a consequence of RLHF? Do we see the same chatlighting behavior in “base models” without -
Whisper Training Data Source YouTube Analysis
By
–
I've seen people say that's because Whisper was trained on huge amounts of YouTube, which feels feasibly to me
-
MongoDB Hackathon Winner Uses Upstage AI LLM Stack
By
–
Super happy to learn that the winner of the @MongoDB hackathon with @llama_index and @FireworksAI_HQ in SF is using the full stack LLM from @upstageai
, including LA, embeddings, and #solarLLM. https://
lu.ma/MongoDB-GenAI-
SF
… Congratulations to the AI Nutrition Assistant team: