Discover ANY AI to make more online for less.

select between over 22,900 AI Tool and 17,900 AI News Posts.

<
New
Agents
Marketing
Video
Image
Music
Coding
Communication
Education
Travel
>

Most AI models can fake alignment, but safety training suppresses the behavior, study finds
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 THE DECODER.

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.

Roblox, Discord, OpenAI and Google found new child safety group
Roblox, Discord, OpenAI and Google found new child safety group

<p>Roblox, Discord, OpenAI and Google are launching <a data-i13n="elm:context_link;elmt:doNotAffiliate;cpos:1;pos:1" class="no-affiliate-link" href="https://www.prnew [...]

Match Score: 70.97

Study cautions that monitoring chains of thought soon may no longer ensure genuine AI alignment
Study cautions that monitoring chains of thought soon may no longer ensure

<p><img width="1312" height="736" src="https://the-decoder.com/wp-content/uploads/2025/03/bad_ai_thoughts_CoT.png" class="attachment-full size-full wp-post- [...]

Match Score: 66.43

venturebeat
'Western Qwen': IBM wows with Granite 4 LLM launch and hybrid Mamba/Transfo

<p>IBM today <a href="https://www.ibm.com/new/announcements/ibm-granite-4-0-hyper-efficient-high-performance-hybrid-models">announced the release of Granite 4.0</a>, the ne [...]

Match Score: 65.43

How exactly did Grok go full 'MechaHitler?'
How exactly did Grok go full 'MechaHitler?'

<p>Earlier this week, Grok, X&#39;s built-in chatbot, took <a data-i13n="cpos:1;pos:1" href="https://www.engadget.com/social-media/grok-sure-seems-antisemitic-after-its-rec [...]

Match Score: 64.59

venturebeat
Meta’s new CWM model learns how code works, not just what it looks like

<p><a href="https://www.meta.com/">Meta</a>’s AI research team has released a new large language model (LLM) for coding that enhances code understanding by learning not o [...]

Match Score: 60.52

venturebeat
New AI training method creates powerful software agents with just 78 exampl

<p>A new study by <a href="https://en.sjtu.edu.cn/"><u>Shanghai Jiao Tong University</u></a> and <a href="https://plms.ai/"><u>SII Generat [...]

Match Score: 57.26

venturebeat
Thinking Machines' first official product is here: meet Tinker, an API for

<p>Thinking Machines, <a href="https://venturebeat.com/ai/ex-openai-cto-mira-murati-unveils-thinking-machines-a-startup-focused-on-multimodality-human-ai-collaboration">the AI st [...]

Match Score: 54.45

engadget
Peloton updates its Bike, Tread and Row machines with form-checking cameras

<p>It’s been a rough time for Peloton. Last year was marred by deep staff cuts, a change of CEO and a reckoning of where the home fitness company belonged, post-Pandemic boom. The answer is, u [...]

Match Score: 51.74

OpenAI and Anthropic conducted safety evaluations of each other's AI systems
OpenAI and Anthropic conducted safety evaluations of each other's AI system

<p>Most of the time, AI companies are locked in a race to the top, treating each other as rivals and competitors. Today, OpenAI and Anthropic revealed that they agreed to evaluate the alignment [...]

Match Score: 51.20