OpenAI is rumoured to push major developer-friendly updates for cost-effective application building at their november 6th developer conference. Adding memory storage and vision capabilities, targeting ambitious revenue goals, launching stateful and vision APIs, focusing on
LLMS
-
7 Tips to Mitigate LLM Hallucinations in Production
By
–
Good morning fellow AI enthusiast! This is the second iteration of my new video series for our free course "Training & Fine-Tuning LLMs for Production"! Dive into my favorite LLM-related topic, Hallucinations, with 7 tips to mitigate them: https://
open.substack.com/pub/louisbouch
ard/p/7-tips-to-mitigate-hallucinations?r=25qlky&utm_campaign=post&utm_medium=web
… -
Learning Text Embeddings with Cohere and LLMU
By
–
You can learn more about text embeddings from @SerranoAcademy with LLMU: https://
docs.cohere.com/docs/text-embe
ddings
… -
Understanding Text Embeddings: How NLP Captures Language Meaning
By
–
How does natural language processing (NLP) capture the meaning of language so well? Here’s AI scientist and LLM University lead Luis Serrano with a simple explanation of text embeddings. Enjoy. pic.twitter.com/mANM5wkqbs
— Cohere (@cohere) 13 octobre 2023How does natural language processing (NLP) capture the meaning of language so well? Here’s AI scientist and LLM University lead Luis Serrano with a simple explanation of text embeddings. Enjoy.
-
GPT-4 Recognizes Famous ML Equations Without Explicit Labels
By
–
I should note that these example equations are pretty famous – they're for cross-entropy and adam optimiser; obviously GPT4 recognised them, since it named the functions correctly, although I never said what they were. Perhaps for less-known equations it would be less good.
-
ChatGPT Completes Tests in Record Time
By
–
Cool in the time it took to write that ChatGPT finished running its tests
-
Do Mistral Fine-Tunes Achieve Exceptional TruthfulQA Scores?
By
–
Do all mistral fine-tunes have insane truthfulqa scores?
-
Why MMLU Performance Lags Behind Other AI Evaluation Benchmarks
By
–
Very cool. I wonder why MMLU is much worse than other evals here
