Tech & Society
Mistral AI Extends Its Portfolio: Mistral enhances AI landscape in Europe with Microsoft partnership and new language models.
European AI champion Mistral AI unveiled new large language models and formed an alliance with Microsoft.
Latest
Machine Learning Research
Human Feedback Without Reinforcement Learning: Direct Preference Optimization (DPO) fine-tunes pretrained large language models on human preferences without the cumbersome step of reinforcement learning.
Reinforcement learning from human feedback (RLHF) is widely used to fine-tune pretrained models to deliver outputs that align with human preferences. New work aligns pretrained models without the cumbersome step of reinforcement learning.
Machine Learning Research
Swiss Army LLM
The combination of language models that are equipped for retrieval augmented generation can retrieve text from a database to improve their output. Further work extends this capability to retrieve information from any application that comes with an API.
Machine Learning Research
Better, Faster Network Pruning: Researchers devise pruning method that boosts AI speed
Pruning weights from a neural network makes it smaller and faster, but it can take a lot of computation to choose weights that can be removed without degrading the network’s performance.
Tech & Society
OpenAI’s Next Act?: OpenAI sets its sights on autonomous digital assistants.
OpenAI is focusing on autonomous agents that take action on a user’s behalf. The maker of ChatGPT is developing applications designed to automate common digital tasks by controlling apps and devices, The Information reported.
Hardware
Blazing Inference Speed: Groq elevates AI processing speed with advanced chips.
An upstart chip company dramatically accelerates pretrained large language models. Groq offers cloud access to Meta’s Llama 2 and Mistral.ai’s Mixtral at speeds an order of magnitude greater than other AI platforms. Registered users can try it.
Tech & Society
Context Is Everything: Gemini 1.5 Pro, a leap in multimodal AI amid controversy over v1.0
An update of Google’s flagship multimodal model keeps track of colossal inputs, while an earlier version generated some questionable outputs.
Data Points
The latest in AI from Feb. 22 to Feb. 28, 2024
This week's top AI news and research stories featured Google's troubled Gemini launch, OpenAI's next act, Groq's blazing inference speed, and a method for faster network pruning. But first:
Letters
The Python Package Problem: Python packages can give your software superpowers, but managing them is a barrier to AI development.
I think the complexity of Python package management holds down AI application development more than is widely appreciated. AI faces multiple bottlenecks — we need more GPUs, better algorithms, cleaner data in large quantities.
The Batch Newsletter
Google's Troubled Gemini Launch, OpenAI's Next Act, Groq's Blazing Inference Speed, Faster Network Pruning
The Batch AI News and Insights: I think the complexity of Python package management holds down AI application development more than is widely appreciated. AI faces multiple bottlenecks — we need more GPUs, better algorithms, cleaner data in large quantities.
Machine Learning Research
Memory-Efficient Optimizer: A method to reduce memory needs when fine-tuning AI models
Researchers devised a way to reduce memory requirements when fine-tuning large language models. Kai Lv and colleagues at Fudan University proposed low memory optimization (LOMO), a modification of stochastic gradient descent that stores less data than other optimizers during fine-tuning.
Tech & Society
Gymnastics Judge’s Helper: AI system measures performances in Olympic-level gymnastics competitions.
Judges in competitive gymnastics are using an AI system to double-check their decisions.