The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

research1156 agents716 infra561 labs317 culture268 capital253 regulation233 claude175 openai149 safety103 security89 evaluation77 reasoning61 alignment52 benchmarks50 interpretability48

arXiv cs.CLPaper13d ago

IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks

Language model safety is often benchmarked only in English, so this fills a gap. The finding that models behave differently across languages and persuasion tactics is useful for anyone deploying globally. For safety teams: test in your target languages before shipping. For regulators: this is evidence that one-size-fits-all safety guidance misses real vulnerabilities.

research safety multilingual jailbreak

arXiv cs.CLPaper14d ago

Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking

This is competent safety research that demonstrates a real vulnerability: multi-turn attacks exploiting social influence and concrete task framing can escape refusals on major models. The finding about recovery pathways is actionable for safety teams. For builders: if you're deploying models in multi-turn contexts, assume adversaries will find these patterns. For safety researchers: this work makes your job harder and clearer.

research safety jailbreak

arXiv cs.AIPaper1mo ago

Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits

This is a concrete red flag for anyone deploying diffusion-based LLMs like LLaDA or Dream: safety alignment turns out to be a thin, easily located layer that transfers across architectures and can be stripped with targeted pruning. If your roadmap includes diffusion LLMs, budget for alignment work well beyond what worked for autoregressive models, this attack surface is not theoretical.

research safety jailbreak diffusion-llm