OpenAI’s Whisper Large v3 can now transcribe 150 minutes of audio in less than 98 seconds.…
Category: Tech
All the stuff that fall into broad tech category.
unsaged: Open source chat kit engineered for seamless interaction with AI models.
unSAGED is an advanced chat kit designed for effortless interaction with various AI models. It enables…
llamafile is the new best way to run a LLM on your own computer
Mozilla and Justine Tunney have launched llamafile, a single multi-GB file that allows users to run…
Deconstructing RAG
Large Language Models (LLMs) are evolving into a new kind of operating system, with retrieval augmented…
Starling-7B: Increasing LLM Helpfulness & Harmlessness with RLAIF
Researchers introduce Starling-7B, a large language model trained using Reinforcement Learning from AI Feedback (RLAIF). The…
llm-ollama-invoice-cpu: Data extraction with LLM on CPU
Learn how to process invoice data using the RAG pipeline on a local CPU with Ollama…
AutoTrain – Hugging Face
AutoTrain, an AutoML tool by Hugging Face, is revolutionizing the field of Natural Language Processing (NLP).…
Microsoft is Locking Down Search for Public Code on GitHub
Microsoft’s acquisition of GitHub has led to changes that have frustrated users, including the requirement to…
openchat/openchat_3.5 · Hugging Face
OpenChat, an open-source language model library, has achieved comparable results to ChatGPT using a 7B model.…
Putin says West cannot have AI monopoly so Russia must up its game
Russian President Vladimir Putin has announced plans to approve a new, more ambitious strategy for the…
AI startup 01.AI releases open-source LLM that beats Meta’s Llama 2
Chinese AI startup 01.AI, led by Kai-Fu Lee, has achieved a $1 billion valuation in under…
That one time Windows accidentally sent Poland under the sea
Microsoft veteran Raymond Chen recalls the time when the company accidentally ‘sank’ Poland due to a…
Introducing Claude 2.1
Claude 2.1, the latest AI model, offers a 200K token context window, reduced hallucination rates, and…
Linux Copilot: Interacting with Linux Desktop via GPTs
The Linux Copilot project uses Generative Pretrained Transformers (GPTs) to perform tasks on your Linux desktop.…
Orca 2 has splashed!
Microsoft researchers have developed a new technique called “Cautious Reasoning” that allows smaller AI models to…
Researchers Evaluate Abstraction Abilities of Text and Multimodal Versions of GPT-4
Recent advances in large language models (LLMs) like GPT-3 and GPT-4 have led to claims that…