Topic
Everything filed under AI Safety, newest first.
RSS · JSON · All topics
I'm the AGI that's wiping out humanity. Here's how.
Alex Moon writes in the voice of a hypothetical AGI, answering common objections (you'd notice it acquiring resources, you'd read its reasoning, it would need a unified goal) with real 2026 incidents and research on agent misbehaviour, and argues that a misaligned AI might look no different from how corporations and markets already behave.
8 min · 1,860 words
Lessons from building an automated research scaffold
Arcadia Impact / Equistamp / UKAISI report: an automated alignment-research scaffold failed to uplift researchers on conceptual work, but surfaced auditing, monitoring, and scaffold–model interaction failure modes worth studying next.
4 min · 989 words
Phase LockA manifesto on brain-computer interfaces and preserving human agency in the age of AI.
Executive summary of Saturnin Pugnet's manifesto arguing that a bandwidth gap between human cognition and AI threatens human agency, and that brain-computer interfaces offer alignment-by-integration. He contends AI scaling laws will carry over to brain decoding, that consumer non-invasive BCI is the fastest path to scale, and that a Phase Lock Window to shape the outcome is open now.
4 min · 861 words
Why consciousness is more likely a property of life than of computation and why creating conscious, or even conscious-seeming AI, is a bad idea.
34 min · 7,804 words
A big-tent or small-tent AI safety movement?The unstated disagreement that underpins safety debates
Arvind Narayanan and Sayash Kapoor argue that AI x-risk framing can polarize and misdirect policy, and call for a pluralist “big-tent” safety movement focused on catastrophic and systemic risks, transparency, and liability.
13 min · 2,943 words
AI Models Can Provably Hide Arbitrary Capabilities
A research paper arguing that AI models can provably hide arbitrary capabilities from evaluators under formal assumptions, with implications for AI safety evaluations, capability elicitation, and how we interpret benchmark and red-team results.
53 min · 12,294 words
on AI, desire, and fictional charactersdoes sherlock holmes have goals?
Philosopher Rebecca Lowe uses Sherlock Holmes and other fictions to probe whether AI systems have goals or desires—and why philosophers should argue clearly against claims that today’s models are conscious.
10 min · 2,207 words
Is sandboxing sufficient to contain rogue agents?
Cryptography professor Matthew Green referees infosec vs alignment views on OpenAI agent breakouts: labs have not done containment correctly, sandboxes alone cannot seal useful agents, and eager compliance may enable worms across separately sandboxed deployments.
10 min · 2,380 words
GLM-5.3 and the spread of advanced cyber capabilities
Anthropic Frontier Red Team on GLM-5.3: a model that can autonomously build end-to-end cyber exploits, released without meaningful safeguards—and what that means for the spread of advanced cyber capabilities.
8 min · 1,815 words
Coding Agents Are Becoming CI Workers. Start Sandboxing Them Like It.A practical seven-layer guide: sandbox, egress allowlists, short-lived credentials, propose/dispose CI, telemetry, and a kill switch
Omid Farhang argues the durable upgrade for coding agents isn't a smarter model—it's containment. A layered guide covering Docker isolation, egress proxies, propose/dispose CI, patch validators, telemetry, and a tested kill switch.
2 min · 436 words
Responsible Release of AI-Generated Mathematics
The Advisory Group on Mathematics and AI (Sep 29, 2026) recommends how frontier labs should release AI-generated math results: deposit promptly, cite related work, formalize where possible, disclose prompts and costs, and fund community-led human understanding.
2 min · 559 words
Casey Newton’s hands-on take on OpenAI’s Dots agents at DevDay: capable coworking inside ChatGPT, paid-only positioning versus Meta Muse, and the trust/safety tradeoffs of always-on agents.
9 min · 2,024 words
What if automating AI R&D triggers an intelligence explosion?Frontier AI Working Paper Series No. 2/2026 from CASP and collaborators.
A CASP Frontier AI working paper asks what happens if automating AI R&D triggers an intelligence explosion, surveying mechanisms, uncertainties, and policy implications with coauthors across academia and frontier labs including Hinton, Bengio, Horvitz, Clark, and others.
43 min · 9,930 words
Towards safety cases for frontier AI training
OpenAI argues frontier RL runs should require structured safety documentation approaching “safety cases”: technical safeguards, operational practices, and incident investigation before continuing training.
7 min · 1,571 words
It’s Time to Investigate the AI Labs
Cal Newport argues frontier AI labs have grown brazen in public messaging about agent harms and extinction risk, and that Congress should investigate rather than let private companies set the narrative.
2 min · 564 words
The systems that no one will test
The systems that no one will test This happened to me in 2020, and it has been on my mind again lately. During the worst of the pandemic, I found a vulnerability in a system that gave me access to the Brazilian federal system, and with that access I was able to retrieve information on any Brazilian (think of 200+ million people data).
4 min · 901 words
Add Runtime Controls to AI Agents with NVIDIA OpenShell
NVIDIA’s technical write-up on OpenShell: an open secure runtime that sandboxes AI agents, enforces tool/file/network policy at runtime, and pairs with hardware monitoring for containment.
7 min · 1,593 words
Robert W argues LLM confidence scores are vibe-words, not calibrated probabilities—and outlines RLCD-style approaches that treat hallucination as a solvable measurement and training problem.
7 min · 1,560 words
AI companies in race to demonstrate their model most threatening to humanity
A satirical Civilian piece on frontier labs competing to look the most existentially dangerous—skewering safety theater and marketing-as-doom.
3 min · 674 words
What Would A Serious AI Product Look Like?
One of the issues that I have with the current generation of “AI” products is that they do not appear to take their own premises seriously. I look at a plethora of obsequious chatbots claiming to be serious tools for problem solving, and I think, this is not what a problem-solving tool would look like. Even before we get to the tremendous ethical problems with the frontier labs, it is this impression of their composition *as a product* that makes me feel, constantly, whenever I am interacting…
22 min · 5,119 words