Firehose

Mux is the video API that translates audio and answers questions about your video. Get $50 in free credits: https://mux.com/fireship Ex-OpenAI researcher Diogo Almeida spent two years in stealth building Jev, a "System 1" AI model that can'…

This paper proposes a way to align language models with human values by learning to prioritize different moral values in different situations, and shows that this can lead to more accurate and fair decision-making. Practitioners might care because they want to use language models in applications where values and morality are important, such as in healthcare, law, or education.

This paper investigates whether giving a language model extra information, such as a worked solution, improves its learning through on-policy self-distillation. A practitioner might care about how to optimize this technique for better performance.

This paper aims to automate end-to-end business intelligence (BI) tasks using large language models (LLMs), making it easier for users to answer business questions without manual data preparation. Practitioners might care about this research because it could improve the efficiency and productivity of BI workflows.

Gemini 3.8 Live and 3.8 Live Extended Thinking models have been launched, offering fast and fluid conversations with real-time visual and language support. These models can handle complex reasoning, background task execution, and interruptions without disrupting the conversation. AI summary

Tim Scarfe interviews the Tufa Labs ARC-AGI-3 team to dissect their winning approach on the ARC-AGI-3 benchmark, focusing on how their system discovers goals and balances exploration with action efficiency. The episode explores the challeng…