Zoom researchers detail a “chain of draft” method to let LLMs accurately solve reasoning problems with as little as 7.6% of the tokens used by current methods.
Mistral launches Mistral OCR, a multimodal API that can turn complex PDF documents into AI-ready Markdown files.
Alibaba releases QwQ-32B, an open-source reasoning model, on Hugging Face and ModelScope, claiming performance similar to DeepSeek-R1 with lower compute needs.
AMD Announces "Instella" Open-Source 3B Language Models.
AI Chatbots Can Cushion the High School Counselor Shortage — But Are They Bad for Students?
The L.A. Times adds AI-generated counterpoints to its opinion pieces and guess what, there are problems.
‘I can’t be friends with the machine’: what audio artists working in games think of AI.
OpenAI unveils NextGenAI, a consortium of research institutions including Harvard, MIT, and Oxford, and commits $50M in compute, API access, and research grants.
Microsoft unveils Sales Agent and Sales Chat AI agents, available in public preview in May, designed to work with Dynamics 365 business apps and with Salesforce.
Microsoft unveils Dragon Copilot, a new voice-activated AI assistant for doctors.
The AI Hoax is Destroying America with Ed Zitron
Hallucinations in code are the least dangerous form of LLM mistakes.
Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone.
Nearly all UK undergraduate students use AI in their studies, according to new survey results.
Openai introduce GPT-4.5 .
OCTAVE: the first text-to-speech model that understands what it’s saying.
IBM Expands Granite Model Family with New Multi-Modal and Reasoning AI Built for the Enterprise.
Microsoft released Phi-4-multimodal(5.6B parameter) and text only Phi-4-mini(3.8B parameter), Small language models.
China's DeepSeek 'shared user data' with TikTok owner ByteDance, South Korea says, removes app from its stores
New Open Source AI model beats DeepSeek's performance using just 14% of the data its Chinese competitor needed
.png?format=webp&thumbnail=256)
