For instance, Edison Scientific’s Kosmos, launched on 7 November, claims to complete six months of research in a single day, reading 1,500 papers and producing structured analyses in one run. In theory, AI can now turn a single prompt into a full-fledged hypothesis, generate...
ChatGPT is about to become faster and more conversational as OpenAI upgrades its flagship model GPT-5 to GPT-5.1.OpenAI announced two updates to the GPT-5 series: GPT-5.1 Instant and GPT-5.1 Thinking. Both models are now accessible on ChatGPT. GPT-5.1 Instant, essentially the default and most-used model, is now “warmer, more intelligent, and better at following your instructions,” according to OpenAI. Meanwhile, GPT-5.1 Thinking is an...
Researchers at Meta FAIR and the National University of Singapore have developed a new reinforcement learning framework for self-improving AI systems. Called Self-Play In Corpus Environments (SPICE), the framework pits two AI agents against each other, creating its own challenges and gradually improving without human supervision.While currently a proof-of-concept, this self-play mechanism could provide a basis for future AI systems that can dynamically...
For decades, Google has developed privacy-enhancing technologies (PETs) to improve a wide range of AI-related use cases. Today, we’re taking the next step in building helpful experiences that keep users safe with Private AI Compute in the cloud, a new AI processing platform that combines our most capable Gemini models from the cloud with the same security and privacy assurances you expect from...
When the history of AI is written, Steven Adler may just end up being its Paul Revere—or at least, one of them—when it comes to safety.Last month Adler, who spent four years in various safety roles at OpenAI, wrote a piece for The New York Times with a rather alarming title: “I Led Product Safety at OpenAI. Don’t Trust Its Claims About ‘Erotica.’”...
