the-decoder3 天
"Nerd sniping" and "think less" attacks emerge as AI models get more time to reason
A new study by OpenAI shows that AI models become more robust against manipulation attempts if they are given more time to "think". The researchers also discovered new methods of attack. A recent ...
the-decoder3 天
OpenAI's Operator and Computer-Using Agent bring autonomous AI agents closer to reality
OpenAI has just launched Operator, an AI assistant that can navigate the web on its own. The tool, currently only available to US ChatGPT Pro subscribers, represents a step toward AI assistants that ...
the-decoder6 天
DeepSeek's latest R1-Zero model matches OpenAI's o1 in reasoning benchmarks
Chinese AI startup DeepSeek has released two new AI models that they say match OpenAI's o1 in performance. Along with their main models, DeepSeek-R1 and DeepSeek-R1-Zero, they've also launched six ...
the-decoder3 天
Perplexity announces new assistant for Android smartphones
Perplexity is stepping into Google's territory with a new AI assistant for Android that can control apps and handle tasks on its own. The move puts the startup in direct competition with Google's ...
the-decoder7 天
OpenAI quietly funded independent math benchmark before setting record with o3
OpenAI's involvement in funding FrontierMath, a leading AI math benchmark, only came to light when the company announced its record-breaking performance on the test. Now, the benchmark's developer ...
the-decoder3 天
AI image generation gets a boost by borrowing ideas from reasoning models
A team of researchers from NYU, MIT, and Google has found a way to improve AI-generated images by borrowing ideas from recent AI reasoning models like OpenAI's o1. Their approach enhances image ...
the-decoder6 天
OpenAI CEO Altman tells followers to "chill and cut expectations 100x" amid AGI hype
OpenAI's AI reasoning expert Noam Brown says there is "lots of vague AI hype" on social media. While acknowledging there are "good reasons to be optimistic" about AI progress, Brown emphasized that ...
the-decoder6 天
Sakana AI's Transformer² is a new approach to help language models learn
While today's AI systems are typically trained once to handle various tasks like writing text and answering questions, they often struggle with new, unexpected challenges. Transformer² aims to solve ...
the-decoder28 天
Deepseek's V3 is the latest example of state-controlled censorship in Chinese LLMs
Users have discovered a way to bypass Deepseek V3's content filters through prompt engineering. By asking the model to insert periods between letters, they can get it to provide more balanced or China ...
the-decoder18 天
Companies prioritize AI training over job cuts, WEF study finds
A new World Economic Forum study reveals an interesting tension: while many companies see AI replacing some jobs, they're betting bigger on retraining than layoffs. The WEF's "Future of Jobs Report ...
the-decoder1 个月
Deepseek's $5.6M Chinese LLM wonder shakes up the AI elite
A Chinese startup is proving you don't need deep pockets to build world-class AI. Deepseek's latest language model goes head-to-head with tech giants like Google and OpenAI - and they built it for a ...