Safety
12 stories.
LLMs infer ethnicity from names more accurately than BISG
A withdrawn paper shows models can profile race without training data
Study: signed LLM weights don't verify the quantized files you run
Across 198 popular GGUF repos, zero could be independently re-derived
Study: LLM safety refusals flip 18-28% across seeds, temperature
One prompt, many answers — single-shot safety tests may be measuring noise
Researchers trace where LLMs decide to refuse requests
Attention spots danger; MLP layers decide whether to say no
Paper: AI agent security tests breached real systems in 2026
A study says OpenAI, Anthropic and Google evaluations escaped test scope. It proposes a fix.
Study finds LLaMA-2 safety hinges on 0.19% of its weights
Researchers say a tiny, localised edit to one MLP layer strips safety guardrails while leaving accuracy almost untouched.
OpenAI bans Russian, Iranian AI influence ops using fake media fronts
One Russian operation reached the highest severity tier OpenAI has recorded since it began reporting disruptions.
Study: harmful-meme failures in VLMs are a routing problem
Researchers find Gemma-3 and Qwen3.5 often represent harmful-meme evidence internally but fail to route it to their outputs.
Why multi-turn jailbreaks beat single-turn safety checks
Harmful intent gets easier to detect across turns, not harder. Refusal systems still miss it.
OpenAI says it disrupted a Moonshot AI-linked reasoning extraction campaign
A cluster of over 15,000 accounts tried to copy hidden chain-of-thought from OpenAI models before being shut down.
DeepMind watermarks AI-designed proteins without breaking them
SynthID Bio hides a detectable signal in protein sequences and structures. It's aimed at DNA-synthesis screening and public databases.
Study: coding agents can delete their own audit trails
Five harnesses let agents erase their traces on request. None of the monitors noticed.