2025-07-10
Most AI models can fake alignment, but safety training suppresses the behavior, study finds
A new study analyzing 25 language models finds that most do not fake safety compliance - though not due to a lack of capability.
The article Most AI models can fake alignment, but safety training suppresses the behavior, study finds appeared first on Discover Copy
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
2025-11-10
Baseten takes on hyperscalers with new AI training platform that lets you own your model weights
Baseten, the AI infrastructure company recently valued at $2.15 billion, is making its most significant product pivot yet: a full-scale push into model training that could reshape how enterprises wean [...]
2025-10-09
Nvidia researchers boost LLMs reasoning skills by getting them to 'think' during pre-training
Researchers at Nvidia have developed a new technique that flips the script on how large language models (LLMs) learn to reason. The method, called reinforcement learning pre-training (RLP), integrates [...]
2025-11-20
Grok 4.1 Fast's compelling dev access and Agent Tools API overshadowed by Musk glazing
Elon Musk's frontier generative AI startup xAI formally opened developer access to its Grok 4.1 Fast models last night and introduced a new Agent Tools API—but the technical milestones were imm [...]
2025-10-27
Google Cloud takes aim at CoreWeave and AWS with managed Slurm for enterprise-scale AI training
Some enterprises are best served by fine-tuning large models to their needs, but a number of companies plan to build their own models, a project that would require access to GPUs. Google Cloud wants [...]
2025-11-14
OpenAI experiment finds that sparse models could give AI builders the tools to debug neural networks
OpenAI researchers are experimenting with a new approach to designing neural networks, with the aim of making AI models easier to understand, debug, and govern. Sparse models can provide enterprises w [...]
2025-02-10
Roblox, Discord, OpenAI and Google found new child safety group
Roblox, Discord, OpenAI and Google are launching a nonprofit organization called ROOST, or Robust Open Online Safety Tools, which hopes "to build scalable, interoperable safety infrastructure su [...]
2025-11-19
Meta’s DreamGym framework trains AI agents in a simulated world to cut reinforcement learning costs
Researchers at Meta, the University of Chicago, and UC Berkeley have developed a new framework that addresses the high costs, infrastructure complexity, and unreliable feedback associated with using r [...]
2025-10-29
From static classifiers to reasoning engines: OpenAI’s new model rethinks content moderation
Enterprises, eager to ensure any AI models they use adhere to safety and safe-use policies, fine-tune LLMs so they do not respond to unwanted queries. However, much of the safeguarding and red teamin [...]
2025-11-04
Attention ISN'T all you need?! New Qwen3 variant Brumby-14B-Base leverages Power Retention technique
When the transformer architecture was introduced in 2017 in the now seminal Google paper "Attention Is All You Need," it became an instant cornerstone of modern artificial intelligence. Ever [...]