Delete   Set public   Set private

Picture Wall - 129 pics

When ChatGPT summarises, it actually does nothing of the kind.
Chrome Built-in AI Doesn't Require The Internet
My finetuned models beat OpenAI’s GPT-4
Mapping the Mind of a Large Language Model at Anthropic
Inflection-2.5: meet the world's best personal AI
Introducing Claude 3.5 Sonnet
LLMs are insecure
Perplexity AI Is Lying about Their User Agent
Introducing Lamini Memory Tuning: 95% LLM Accuracy, 10x Fewer Hallucinations
Literal AI - Multi-modal LLM observability and evaluation platform
Your AI Product Needs Evals
What We Learned from a Year of Building with LLMs (Part I)
Mirascope | LLM toolkit for lightning-fast, high-quality development
Semantic Cache: Accelerating AI with Lightning-Fast Data Retrieval
AI Inference now available in Supabase Edge Functions
vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
Model-based evaluations - Langfuse
OpenBioLLM-Llama3-70B
A l'intérieur des LLMs: comprendre les tokens - Generative AI France
Tiny but mighty: The Phi-3 small language models with big potential
mistral.rs: Blazingly fast LLM inference.
Backend ressources for Albert. Albert, also known as LIA (Legal Information Assistant), is a conversational agent that uses official French data sources to answer administrative agents questions.
HuggingFaceFW - FineWeb dataset
IA pas que la Data : #7 - AI Act / Normes ISO : une nécessité pour une IA éthique et de confiance ?
InstructLab - synthetic data-based alignment tuning method for Large Language Models
Meta Llama 3
Tarifs de l'API Gemini  |  Google AI for Developers
FreeAskInternet is a completely free, private and locally running search aggregator & answer generate using LLM
L’IA Générative au service de la pédagogie
huggingface/text-generation-inference: Revert license to Apache 2.0
NVIDIA ChatRTX
AutoRFP.ai Pricing
Air Canada Has to Honor a Refund Policy Its Chatbot Made Up
Introducing Gemini 1.5, Google's next-generation AI model
Self-Rewarding Language Models
voyage-code-2: Elevate Your Code Retrieval
New embedding models and API updates
Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study | Live Science
IA. Le bot du Pôle emploi autrichien refuse d’orienter les femmes vers l’informatique
AlphaGeometry: An Olympiad-level AI system for geometry
A Guide to Large Language Model Abstractions
5 cas d’usage de Chat GPT en Customer Success (+ Prompts associés)
Introducing Canopy: An easy, free, and flexible RAG framework powered by Pinecone | Pinecone
PlugBear: Plug your AI to the world
Inflection - Pi
kapa.ai - ChatGPT for your developer-facing product
Inkeep - Answer developer questions, instantly.
PowerInfer: High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
ChatHub - All-in-one chatbot client
Améliorer la rétention pour les apps LLM
10k-GPT: Upgrading. Implementing BM25 (text) search…
reworkd/tarsier: Vision utilities for web interaction agents 👀
Turing test on steroids: Chatbot Arena crowdsources ratings for 45 AI models
Phi-2 - Slow inference times on gpu
Mamba-Chat: A chat LLM based on the state-space model architecture 🐍
LLMCompiler: An LLM Compiler for Parallel Function Calling
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
GitHub - Chainlit/chainlit: Build Python LLM apps in minutes ⚡️
Chain of Code
Rivet - IA builder
RETVec is an efficient, multilingual, and adversarially-robust text vectorizer.
Langflow - Create your LLM App!
The 6 Types of Conversations with Generative AI
Du nouveau dans Workers AI : bonjour Mistral 7B
RLHF: Reinforcement Learning from Human Feedback
An open platform for training, serving, and evaluating large language model for tool learning.
CoT-Igniting-Agent
OpenChat 3.5 basé sur Mistral est comparable à ChatGPT
AI proxy: fostering a more open ecosystem
ishan0102/vimGPT: Browse the web with GPT-4V and Vimium
Lindy.ai — Meet Your AI Employee
Filtrable HNSW - Qdrant
Prompt Engineering on OpenAI Platform
Generative AI exists because of the transformer
Vector indexes for Embedding
GitHub - kyegomez/tree-of-thoughts: Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
GitHub - danswer-ai/danswer: Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc.
Retrieval Augmented Generation (RAG): Reducing Hallucinations in GenAI Applications
The Prompt Landscape
Multi-modal prompt injection image attacks against GPT-4V
dair-ai/ML-Papers-of-the-Week: 🔥Highlighting the top ML papers every week.
Pas d’interdiction de ChatGPT chez Carrefour, mais une sensibilisation des équipes
Vercel AI SDK Playground
LMQL: Programming Large Language Models
15 times Faster than Llama 2: Introducing DeciLM - NAS-Generated LLM with Variable GQA
KillianLucas/open-interpreter: OpenAI's Code Interpreter in your terminal, running locally
Meaningful Code Tests for Busy Devs | CodiumAI
spcl/graph-of-thoughts: Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
MineDojo/Voyager: An Open-Ended Embodied Agent with Large Language Models
kyrolabs/awesome-langchain: 😎 Awesome list of tools and projects with the awesome LangChain framework
Grit
Normcore LLM Reads
Introducing DeciCoder: The New Gold Standard in Efficient and Accurate Code Generation
morph-labs/rift: Rift: an AI-native language server for your personal AI software engineer
Outlines - Generative Model Programming
Test and deploy your LLM prompts in a data-driven way on an open-source and self-hostable platform
Open LLM Leaderboard - a Hugging Face Space by HuggingFaceH4
Gandalf | Lakera – Test your prompting skills to make Gandalf reveal secret information.
jmorganca/ollama: Get up and running with large language models locally
Meet FreeWilly, Our Large And Mighty Instruction Fine-Tuned Models
AI Playground
Llama 2 is here - get it on Hugging Face
GPT4All
Introducing no-code LLM FineTuning with MonsterAPI
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
HuggingChat
Le coût de fonctionnement de ChatGPT serait faramineux
RedPajama, a project to create leading open-source models, starts by reproducing LLaMA training dataset of over 1.2 trillion tokens
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Web LLM runs the vicuna-7b Large Language Model entirely in your browser, and it’s very impressive
LLM Hacker handbook
The Complete Beginners Guide To Autonomous Agents
Ce qui se cache derrière le fonctionnement de ChatGPT
Auto-GPT, An experimental open-source attempt to make GPT-4 fully autonomous.
A Watermark for Large Language Models
La couleur des mots
Comment les I.A. font-elles pour comprendre notre langue ?
Generative AI Won’t Revolutionize Search — Yet
Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models - Cerebras
Automate your browser with GPT-4
The Implications of Today's HUGE AI Announcements
Arrêtez de révéler tous vos secrets à ChatGPT, vous mettez votre entreprise en danger
GPT-4
Stanford Alpaca, and the acceleration of on-device large language model development
Google et son robot pipoteur(*), selon Doctorow
Outils gratuits d'intelligence artificielle pour détecter le contenu généré via ChatGPT
AIOps
Google Invests Almost $400 Million in ChatGPT Rival Anthropic
OpenAI has hired an army of contractors to make basic coding obsolete