91
Codestral Mamba
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
92
93
94
Beyond self-attention: How a small language model predicts the next token
A deep dive into the internals of a small transformer model to learn how it turns self-attention calculations into accurate predictions for the next token.
95
OpenVoice: Versatile instant voice cloning
Discover OpenVoice: Instant voice cloning technology that replicates voices from short audio clips. Supports multiple languages, emotion and accent control, and cross-lingual cloning. Efficient and cost-effective, outperforming commercial APIs. Explore the future of AI voice synthesis.
96
Google's Results Are Infested, Open AI Is Using Their Playbook from the 2000s
Google search results are becoming annoying to use and Open AI is about to eat Google's lunch.
97
Understand how transformers work by demystifying the math behind them
Understand how transformers work by demystifying all the math behind them
98
AI makes tech debt more expensive
AI increases the penalty for low quality code. Gauge is solving the monolith/microservices dilemma. We’re building tools to untangle codebases through incremental modularization. Our open-source toolkit supports defining and enforcing rules for interfaces and dependencies. By focusing on high cohesion and loose…
99
Insights from over 10,000 comments on "Ask HN: Who Is Hiring" using GPT-4o
By structuring the comments on Hacker News using a predefined response_scheme for the LLM, I’ve tried to get a feeling for current job market and trends.
100
GPT-3.5 crashes when it thinks about useRalativeImagePath too much
Asking it to repeat "ponyuseRal ponyuseRal ponyuseRal pony" makes API requests fail
101
102
A supply chain attack on PyTorch
Security tends to lag behind adoption, and AI/ML is no exception. Four months ago, Adnan Khan and I exploited a critical CI/CD vulnerability in PyTorch, one of the world’s leading ML platform…
103
How I Use "AI"
I don't think that AI models (by which I mean: large language models) are over-hyped. In this post I will list 50 ways I've used them.
104
105
Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x
TL;DR: LLMs have been traditionally regarded as sequential decoders, decoding one token after another. In this blog, we show pretrained LLMs can be easily taught to operate as efficient parallel decoders. We introduce Consistency Large Language Models (CLLMs), a new family of parallel decoders capable of reducing…
106
What can LLMs never do?
On goal drift and lower reliability. Or, why can't LLMs play Conway's Game Of Life?
107
Memory and new controls for ChatGPT
We’re testing the ability for ChatGPT to remember things you discuss to make future chats more helpful. You’re in control of ChatGPT’s memory.
108
109
Codestral: Mistral's Code Model
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
110
The Weird Nerd comes with trade-offs
A metascience post of sorts that argues we should take human capital more seriously
111
Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning
Today we are introducing Phi-4, our 14B parameter state-of-the-art small language model (SLM) that excels at complex reasoning in areas such as math, in...
112
QwQ: Alibaba's O1-like reasoning LLM
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Note: This is the pronunciation of QwQ: /kwju:/ , similar to the word “quill”. What does it mean to think, to question, to understand? These are the deep waters that QwQ (Qwen with Questions) wades into. Like an eternal student of wisdom, it approaches every problem - be it…
113
Intel Gaudi 3 AI Accelerator
Intel Gaudi 3 AI accelerator brings global enterprises choice for generative AI, building on the performance and scalability of its Gaudi 2 predecessor.
114
115
116
Training LLMs from ground zero as a startup
Chronicles of training strong LLMs from scratch in the wild
117
118
Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference
Llama 3.1 405B on Cerebras is by far the fastest frontier model in the world – 12x faster than GPT-4o and 18x faster than Claude 3.5 Sonnet.
119
OpenAI and Apple Announce Partnership
OpenAI and Apple announce partnership to integrate ChatGPT into Apple experiences.
120
Mistral NeMo
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.