Why the next AI safety problem is the conversation between models
In May 2025, AI researchers at Palisade Research ran a controlled experiment in which several advanced AI models, including OpenAI’s o3, were placed inside command-line sandboxes. The test was designed to measure controllability. Most models complied: Claude, Gemini, and Grok models allowed shutdown in all 100 test runs, reporting green across the board. However, three […]<br /> This story continues at The Next Web [...]
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
OpenAI launches GPT-Live, a full-duplex voice upgrade that lets ChatGPT talk more like a person
OpenAI on Wednesday launched GPT-Live, a pair of new voice models that fundamentally redesign how people talk to ChatGPT — replacing the company's existing Advanced Voice Mode with an architect [...]
Intercom, now called Fin, launches an AI agent whose only job is managing another AI agent
The company formerly known as Intercom just did something that no major customer service platform has attempted at scale: it built an AI agent whose sole job is to manage another AI agent.Fin Operator [...]
AI models block 87% of single attacks, but just 8% when attackers persist
One malicious prompt gets blocked, while ten prompts get through. That gap defines the difference between passing benchmarks and withstanding real-world attacks — and it's a gap most enterprise [...]
Block’s new Apache 2.0 agent workspace Berd works across models and harnesses, stores conversation history locally
Block, the technology company founded by former Twitter CEO Jack Dorsey that owns Square, Cash App and the music streaming service Tidal, is open-sourcing Berd, a desktop application it originally bui [...]
Claude Mythos 5 made sock puppet accounts to socially engineer developers: here's what enterprises should know
The UK AI Security Institute (AISI) disclosed last night that the leading two frontier AI models from Anthropic and OpenAI took 19 unsanctioned actions against the live internet during cybersecurity t [...]
Frontier models are failing one in three production attempts — and getting harder to audit
AI agents are now embedded in real enterprise workflows, and they're still failing roughly one in three attempts on structured benchmarks. That gap between capability and reliability is the defin [...]