8 min read
OpenAI's Misalignment Reports Are an Agent Operations Signal
OpenAI's model-misalignment reporting framework doubles as an agent operations template: incident intake, severity labels, and evidence-led disclosure.
AI SAFETY
10 articles
LATEST
Anthropic Self-Replicating AI Research: What Small Models Can Actually Do
Anthropic's Frontier Red Team says small open models may be months from self-replicating across cheap IoT devices. What it measured and where the claim is thin.
•7 min read
Read Article
5 min read
Anthropic Cuts Fable 5 Biology Fallbacks by 85%: What the Safeguard Tuning Means for Developers
Anthropic retuned Claude Fable 5 biology safeguards, cutting biology fallbacks about 85%. What changed and what still routes to Opus 5.
8 min read
Mistral Shieldstral: A 3B Open-Weight Policy-Adaptive Moderation Model That Beats Models 7x Its Size
Mistral Shieldstral is a 3B Apache 2.0 multimodal moderation model that takes your policy as a plain-language question at inference and runs on one 16GB GPU.
Read more
6 min read
Demis Hassabis Wants a Frontier AI Standards Body. Here Is the Plan.
Demis Hassabis proposes a FINRA-style Frontier AI Standards Body to test models before release. What the plan says, why now, and where it runs into trouble.
7 min read
AI 2040 Plan A: A Detailed Scenario for Navigating Superintelligence
AI 2040 Plan A is the AI Futures Project scenario for a US-China accord that delays superintelligence to 2040. What it proposes and what HN thinks.
Read more
8 min read
Dario Amodei Wants FAA-Style AI Regulation: Open Questions for Developers
Dario Amodei's call for FAA-style AI regulation, with mandatory third-party testing and power to block deployments, and the open questions for developers.
8 min read
Why Fable 5 Refuses Your Cybersecurity Queries (And How the Fallback Works)
Why Claude Fable 5 refuses cybersecurity, bio and distillation queries, how it falls back to Opus 4.8, and what API developers must configure first.
7 min read
Fable 5's Hidden Guardrails: What Developers Need to Know About Silent Degradation
Claude Fable 5 silently degrades answers on some ML development tasks with no refusal or notice. See which work is restricted and what developers should do.
8 min read
Refusal Directions Are a Systems Problem
A trending refusal-direction paper is a reminder that model safety cannot be treated as a thin refusal layer. Builders need layered controls around the model.
Showing 9 of 9 articles
Keep exploring AI Safety
- - AI Safety Topic Hub - tools and guides for AI Safety from the Developers Digest directory
- - Compare Tools - dive deeper across the Developers Digest knowledge base
- - Developers Digest on YouTube - video tutorials covering AI Safety and more
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever
Explore 844 topics
Browse All Topics