AI threats in the wild: The current state of prompt injections on the web
Google's Threat Intelligence notes indirect prompt injection (IPI) is a top security priority, but actual exploitation in the wild remains limited.
Google Security Blog·23 Apr
Search signals, briefings, company results, benchmarks and glossary terms.
Search signals, briefings, company results, benchmarks and glossary terms.
Use this view to inspect the underlying evidence corpus. For ranked developments, decision posture and interpretation, use Signals.
Raw feed or Signals?
Raw feed is chronological evidence. Signals ranks and interprets material change.
Google's Threat Intelligence notes indirect prompt injection (IPI) is a top security priority, but actual exploitation in the wild remains limited.
The 'One Useful Thing' newsletter speculates on a hypothetical GPT-5.5 model, suggesting incremental advancements in capability.
OpenAI's GPT-5.5 model is rolling out via ChatGPT and a semi-official Codex backdoor API, with the primary API release delayed for safeguards.
The UK National Cyber Security Centre (NCSC) released guidance on the careful oversight and new capabilities needed for AI adoption in cyber defence.
The UK National Cyber Security Centre (NCSC) details a widespread shift to covert, China-nexus compromised device networks for cyberattacks and defense strategies.
International cyber agencies, including the NCSC, issued new guidance on defending against China-linked covert network tactics in cyber activity.
OpenAI announced GPT-5.5, claiming it is their smartest, fastest model, designed for complex tasks including coding, research, and data analysis.
OpenAI published a 'System Card' for GPT-5.5, a speculative future model, detailing anticipated safety and alignment considerations.
Expert commentary deep dives into advanced AI research covering agent reasoning, multimodal generation, and humanoid learning techniques.
OpenAI launched a bug bounty program for GPT-5.5 Bio, challenging red teamers to find universal jailbreaks for biosafety risks, offering up to $25k.
Shopify CTO details aggressive AI integration, projecting 2026 usage explosion, leveraging Anthropic Opus 4.6 with unlimited tokens.
OpenAI offers ChatGPT for Clinicians at no cost to verified U.S. physicians, nurse practitioners, and pharmacists for clinical, documentation, and research use.
Google DeepMind introduced Decoupled DiLoCo, a new method for distributed AI training designed to improve resiliency and efficiency in large-scale model development.
OpenAI detailed using WebSockets and caching to optimize API response times for agentic workflows, specifically for its Codex agent loop.
Anthropic briefly updated and then reverted its Claude.com pricing page, suggesting a move of 'Claude Code' from the $20/month Pro plan to higher tiers.
OpenAI reportedly launched GPT-Image-2. Cursor secured a $10B contract with xAI, with a $60B acquisition right, as per Latent Space.
OpenAI introduced an open-weight model, OpenAI Privacy Filter, for PII detection and redaction in text with high accuracy.
OpenAI launched ChatGPT Images 2.0, with Sam Altman claiming a performance leap from 1.0 equivalent to GPT-3 to GPT-5. User testing showed improved object recognition and scene composition.
Google DeepMind is collaborating with global consulting firms to expand the deployment of its frontier AI models across various organizations.
Hugging Face launched QIMMA, a quality-first leaderboard for Arabic Large Language Models, evaluating various models on multiple Arabic NLP tasks.
Hugging Face blog post discusses using synthetic personas to ground Korean AI agents in real demographics, improving cultural relevance.
Hugging Face blog post advocates for open-source AI models as a superior approach to cybersecurity compared to proprietary models.
OpenAI launched Codex Labs with Accenture, PwC, Infosys, and other partners to scale Codex enterprise deployment, reaching 4M weekly active users.
Hyatt deploys ChatGPT Enterprise with GPT-5.4 and Codex for global workforce productivity and operations, according to OpenAI.
An industry observer argues that the current state of AI is analogous to the early 20th century's electrification, not the dot-com bubble.
Anthropic updated Claude.ai's system prompt for Opus 4.7, marking an ongoing evolution in model instruction transparency.
PyCon US 2026, a major Python developer conference, will be held in Long Beach, CA, introducing new AI and security tracks.
Anthropic's Claude Opus 4.7 is reportedly a marginal improvement over 4.6, maintaining its position as a leading frontier model.
AI Snake Oil introduces Project CRUX for open-world evaluations of frontier AI on complex, multi-step tasks, addressing current benchmark limitations.
Alibaba's Qwen3.6-35B-A3B quantized model running locally produced a better image than Claude Opus 4.7 for a specific prompt.
Meta developed an AI agent platform to automate finding and fixing performance issues, optimizing infrastructure capacity and freeing engineers.
Donald Trump stated in a Fox Business interview that AI needs a government 'kill switch'. The Future of Life Institute (FLI) noted this.
The Bank of England's Artificial Intelligence Consortium held its February 2026 meeting, fostering public-private dialogue on AI in UK financial services.
OpenAI introduces GPT-Rosalind, a frontier reasoning model for drug discovery, genomics, and scientific research workflows.
OpenAI launched 'Trusted Access for Cyber' program, providing security firms access to GPT-5.4-Cyber and API grants for cyber defense.
Google DeepMind's Gemini 3.1 Flash TTS introduces granular audio tags for expressive AI speech generation, offering precise control.
OpenAI updated its Agents SDK, adding native sandbox execution and a model-native harness for building secure, long-running AI agents.
HCompany introduced HoloTab, an AI browser companion for enhanced web interaction. Details on specific capabilities are limited.
Notion cofounder and Head of AI discuss their journey shipping AI agents for knowledge work, detailing multiple rebuilds and tool integrations.
OpenAI extends its 'Trusted Access for Cyber' program, making an early version of GPT-5.4-Cyber available to vetted cybersecurity organizations.
A speculative timeline by Joe Reis outlines a progression toward autonomous AI models through 2028, focusing on AI's ability to 'think for itself.'
Import AI 453 discusses AI agents, MirrorCode, and a philosophical debate on gradual disempowerment, likening AI to historical paradigm shifts.
Cloudflare integrates OpenAI's GPT-5.4 and Codex into its Agent Cloud, allowing enterprises to develop and deploy AI agents securely.
The Weekend Windup #28 from Joe Reis discusses if fundamental data engineering principles still matter amidst AI advancements.
Reflections on the inaugural AI Engineer Europe conference in London highlighted discussions on the future of AI engineering roles and development.
Leaked files suggest Valve is exploring AI tools to assist moderators on Steam with incident detection and content review.
Google is enhancing Pixel device security by migrating baseband modem firmware to Rust, starting with mitigations in Pixel 9 and expanding for Pixel 10.
HPE is producing modular, containerized data centers designed for rapid deployment to address traditional data center build delays, targeting AI workloads.
OpenAI published a general overview of applications for ChatGPT, Codex, and APIs, focusing on common use cases.
OpenAI published guidance on building custom GPTs for specific tasks, focusing on workflow automation and consistent output generation.
© 2026 OneBench: AI Insights. All rights reserved.
Evidence before opinion