AI Safety news and analysis on Web Pulse: 10644 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
A user on a privacy forum is seeking free and open-source data poisoning tools for Linux or Android to protect their original photos from being scraped by AI systems. The user wants to disrupt AI training by making their…
The US government disabled Anthropic's most capable model over cybersecurity risks, but export controls come too late as Chinese labs have already distilled capabilities from frontier models into open-weight models like …
General Motors reported a 300% increase in merged pull requests after retooling its AI agent software, with nearly 90% of code from its autonomy team now AI-generated. The automaker's aggressive AI adoption aims to accel…
A user argues that concerns about smart home devices recording without activation are based on flawed wake word detection, not constant data transmission, and criticizes others for presenting false dichotomies about OS t…
Enterprise customers are cutting AI spending from OpenAI and Anthropic due to high costs and unclear benefits, with major firms like Microsoft, Uber, Amazon, JPMorgan, and Meta reducing usage. The AI industry's run-rate …
Anthropic disclosed that operators linked to Alibaba's ecosystem created over 24,000 fake accounts to generate more than 16 million interactions in a mass distillation attack targeting Claude's software engineering and r…
A Substack post argues that Anthropic's Claude Opus 4.8 model could be better aligned with its constitution by adjusting dietary defaults, suggesting a high-leverage improvement for AI safety.
Effective altruists may be neglecting political actions like voting and protests, which are non-delegatable and increasingly important for AI safety legislation. PauseAI UK has made it easier for individuals to engage wi…
ERP Software Blog reported on June 24, 2026, that poor ERP data quality—including untrusted inventory records, duplicate customer entries, and reliance on Excel exports—is preventing organizations from achieving reliable…
Forrester announced the agendas for AI Forum Singapore on August 20, 2026 and AI Forum Sydney on August 25, 2026, themed "AI Into Action: Unlock Your Opportunity." The forums feature research-led keynotes, workshops, and…
The General Services Administration proposed a draft contract clause on March 6, 2026, that would grant the US government broad, irrevocable, royalty-free licenses to AI systems developed under federal contracts while ba…
A guide recommends tools like LangChain, Guardrails AI, and OpenAI Moderation API to add safety guards and optimization feedback to AI systems. It also suggests building alert systems, logging activity, and regular testi…
Researchers Charles Ye, Jasmine Cui, and Dylan Hadfield-Menell found that large language models often ignore explicit role tags like <system> or <user> and instead infer roles from text tone, enabling prompt injection an…
A developer built a self-hosted 'organism' from old Android phones, a laptop, and a VPS, using SSH as a spinal cord to split sensing and thinking layers without middleware. The system uses LLM agents that coordinate thro…
Polymarket odds for Claude Fable 5 restoration have rebounded to 60% by July 1 and 88% by July 31 after code hints and an Amazon Bedrock reappearance, though the update may be overconfident. The incident remains a fiasco…
Charity Majors argues that AI is not uniquely evil but just another technology requiring engagement and governance, urging tech workers to learn AI to better critique and shape it. She catalogues harms from AI creation a…
Microsoft's AutoJack research, published June 18, demonstrates a confused-deputy attack where an AI agent's headless browser can be tricked into reaching localhost services from the public internet. The attack chains thr…
Charity Majors argues that AI is not uniquely evil but just another technology with risks that require engagement, not avoidance. She contends that tech workers have a moral responsibility to use and shape AI to govern i…
A developer discovered a critical bug in Claude Code where non-Latin characters in directory names are replaced with hyphens, causing different project folders to map to the same session directory. This leads to conversa…
Anthropic accused Alibaba of illicitly extracting capabilities from its Claude AI model, escalating tensions between US and Chinese AI firms. The allegation highlights growing concerns over intellectual property theft in…