shipping a few new tools for developers today! from last devday to this one: *98% decrease in cost per token from GPT-4 to 4o mini
*50x increase in token volume across our systems
*excellent model intelligence progress
*(and a little bit of drama along the way)
CODE
-
OpenAI Releases Developer Tools with 98% Cost Reduction
By
–
-
Self-Supervised Learning with DINO for Real-World Applications
By
–
Are you curious about self-supervised learning but not sure where to start? This article makes it easy to understand the core concepts of Self-Supervised Learning and introduces you to Facebook AI's DINO model.
— Satya Mallick (@LearnOpenCV) 1 octobre 2024
It also shows how to apply DINO to a real-world challenge: road… pic.twitter.com/EWRfzsw7HsAre you curious about self-supervised learning but not sure where to start? This article makes it easy to understand the core concepts of Self-Supervised Learning and introduces you to Facebook AI's DINO model. It also shows how to apply DINO to a real-world challenge: road
-
Custom Code Assistants with Groq and CodeGPT
By
–
Tune in tomorrow to learn how to create custom code assistants with Groq and @codegptAI
. We'll explain how to use open source models as code assistants in your editor, create agents & enrich them with knowledge through RAG & Knowledge Graphs. -
Efficient logprob encoding using control tokens for low values
By
–
A more efficient way to do this could be to have typical logprobs encoded normally and exceptionally low ones marked with a control token as exact magnitudes don’t matter much beyond them being low — this is the approach of SequenceMatch
-
Add source highlighting to your RAG system for trust
By
–
> Add source highlighting to your RAG system! 📄💡
— m_ric (@AymericRoucher) 1 octobre 2024
RAG systems are supposed to make your LLM's answer more trustworthy, by inserting in the prompt some supporting documents from a knowledge base : we say that we're "adding some context".
👎 But if you don't know which part of… pic.twitter.com/5KmE7wcMua> Add source highlighting to your RAG system! RAG systems are supposed to make your LLM's answer more trustworthy, by inserting in the prompt some supporting documents from a knowledge base : we say that we're "adding some context". But if you don't know which part of
-
OpenAI Announces API Price Cuts and Advanced Features Updates
By
–
API Price Down
Custom GPTs API
Whisper Diarization
API With Search Ground(Search GPT?)
GPT-4o-Turbo
Advanced Voice Mode API
Prompt Caching
Workflow -
Creating Custom Apps with the HuggingFace API
By
–
you can also make your own apps with the api, see: https://
huggingface.co/api/daily_pape
rs
… and docs: -
Automated Summaries of Daily AI Articles with Gemini
By
–
Daily AI Papers Summaries auto-generated from HuggingFace's Daily Papers using Gemini and GitHub Actions. All credits go to the research and HuggingFace communities. You can get audio summaries via OpenAI's text-to-speech API on Telegram.
-
Superwhisper with Custom Instructions for Voice Transcription
By
–
I use superwhisper for that with custom instructions.
-
AnkiGen: LLM-Powered Anki Card Generator Web Application
By
–
AnkiGen Anki Card Generator AnkiGen is a Gradio-based web application that generates Anki-compatible CSV files using Large Language Models (LLMs) based on user-specified subjects and preferences.