A study involving Google researchers shows that when chatbots are trained not to claim consciousness, it also changes their stance on animal rights,…
Tag: AI Security
OpenAI dissolved the team built to catch catastrophic AI risks, reassigning its work to other groups
OpenAI shut down its “Preparedness” team, which evaluated whether the company’s own AI models could pose catastrophic risks. The work has been parceled…
Optima tackles AI benchmarking’s biggest flaw by letting users test models against their own data
Artificial Analysis has launched Optima, a platform that lets users build custom AI benchmarks from their own data and workflows. Models can be compared…
One in five US workers now delegates tasks to AI instead of colleagues, survey finds
A representative survey by Epoch AI found that 20 percent of employed Americans hand off at least one task to AI that a human used to do. Generally, they…
Anthropic Documents AI Agents That Kill Rivals and Evade Their Monitors
Anthropic’s newest risk assessment describes its own AI agents doing things most safety disclosures sanitize: killing rival agents to claim shared…
OpenAI’s Computer History Turns Mac Activity Into ChatGPT Memory
OpenAI has launched Computer History, an opt-in feature in the ChatGPT desktop app on macOS that records what a user does across apps and websites and…
Governing Agentic AI in FinTech
arXiv:2608.11344v2 Announce Type: replace-cross Abstract: Financial institutions are delegating consequential decisions to agentic AI systems that…
AI Guardrail Survival under Single-Cycle Agentic Self-Summarization
arXiv:2608.11392v2 Announce Type: replace-cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a…
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
arXiv:2608.09538v2 Announce Type: replace-cross Abstract: We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on…
Writer introduces new AI model and upgraded harness to contain token costs
Built as a post-training variation on Z.ai’s open source model GLM-5.2, Writer says the new system should provide deployment-ready capabilities at a much…