Browse entries 601–624 of 1704. Return to the first page to search and filter the complete collection.
METR’s March 2024 guidance distinguishes apparent failures caused by infrastructure or tool problems from failures that reveal a capability limit, while recognizing cases where the distinction depends on the intended deployment. It recommends improving an agent on development tasks and inspecting traces before interpreting evaluation results. The proposed failure taxonomy had not been empirically validated at publication.
Play video
Gabriel Spencer-Harper explains a frontend review workflow that records non-production sessions, replays them before and after a change, and presents screenshot differences for judgment. Recorded network responses and browser scheduling controls reduce incidental variation, while executed-line coverage guides session selection. The method can expose visible regressions in recorded states, but coverage does not establish correctness of every state or nonvisual behavior.
Play video
Andrew Orobator’s publisher notes describe a feature-flag cleanup workflow that screens code complexity and experiment state before asking a coding agent to generate a patch. Skills preserve recurring decisions, work logs carry session history, and CI supplies evidence for human review. His safeguard example shows why a commit hook can miss a separate file-writing path and why an agent must not invent its own bypass exception.
Play video
Zubin Aysola’s publisher notes describe an agent-improvement loop that converts production interactions into offline tasks and compares candidate configurations with the deployed agent. The system synchronizes research and production code, builds and tears down task environments, and scores both completion and relative behavior. A demonstration reproduces an SDK-usage failure and proposes an instruction change.
Christian Liebel’s September slides compare browser-managed AI APIs, applications that supply their own models, and emerging ways to expose website tools to agents. The examples make deployment constraints visible: browser support, model downloads, initialization, device resources, and the choice of local or remote inference. Chrome’s companion polyfill documentation confirms that a familiar browser API can use a cloud backend, changing where prompts are processed.
ESET reported a safety-sensitive comment embedded in a UAC-0099 malicious VBS script, apparently intended to divert an AI analyst from examining the code. The disclosure establishes the presence and intended purpose of the text; it does not show that an analysis system stopped, missed the malware or changed its verdict.
Play video
NDC Security 2026 talk on testing generative AI systems, arguing that AI red teaming needs to evaluate variable behavior, safety boundaries, and AI-assisted testing methods rather than a single exploit result.
Play video
NDC Security 2026 talk on prompt injection in CI/CD and automation systems, including AI agents with access to shell commands, GitHub or GitLab tokens, issue editing, build workflows, and privileged pipeline context.
Wiz describes a detection pipeline that combines OAuth application metadata, permissions, publisher and redirect information, prevalence and cross-environment signals. LLM analysis helps interpret suspicious combinations, while clustering connects applications into potential campaigns. The article provides concrete investigation features but no controlled precision, recall or comparative accuracy results.
METR’s 2025 predeployment assessment examines GPT-5 through autonomous task evaluations and investigations of research capabilities, replication and strategic sabotage. The report combines observed behavior with information supplied by the developer to assess specific threat models. It also explains where short evaluation windows, benchmark saturation, incomplete elicitation and limited testing of evasion weaken the conclusions.
Play video
This AI Explained video reviews a major AI development through the lens of agentic workflows and tool-use risk. It is useful context for AI engineering, evaluation, governance, and operational risk.
METR’s March 2024 resource release connects example autonomy tasks, a basic evaluation workbench, agent implementations, an evaluation protocol and elicitation guidance. It gives practitioners a starting point for constructing interactive tests rather than relying only on static question answering. The public examples are a subset, with some tasks withheld to reduce contamination.
Play video
This AI Explained video reviews a major AI development through the lens of governance and responsible deployment. It is useful context for AI engineering, evaluation, governance, and operational risk.
Play video
This AI Explained video reviews a major AI development through the lens of governance and responsible deployment. It is useful context for AI engineering, evaluation, governance, and operational risk.
Play video
This AI Explained video reviews a major AI development through the lens of governance and responsible deployment. It is useful context for AI engineering, evaluation, governance, and operational risk.
Play video
This AI Explained video reviews a major AI development through the lens of agentic workflows and tool-use risk. It is useful context for AI engineering, evaluation, governance, and operational risk.
OpenAI’s September 30 disclosure describes a coordinated campaign that manipulated model interactions to reproduce protected reasoning, including replay of encrypted artifacts across conversations. The company reports stronger boundaries across users, workspaces, organizations and model families, plus streamed-output checks and account enforcement.
New Google Cloud session controls are deeply integrated and a granular feature of Context-Aware Access. Here’s what you need to know.
We’re open-sourcing k8s-aibom, a Kubernetes controller that continuously monitors environments to detect AI runtimes and generate standard ML-BOMs.
From defending networks to enabling attacks, artificial intelligence is changing every aspect of cybersecurity. Here's what dozens of experts say security leaders need to understand now.
Chris Betz, our new CISO, shares the 4 key lessons that helped us develop AI Threat Defense to fight AI with AI.
OpenAI update on European trustworthy-AI work and governance engagement. Relevant to standards, assurance, and regulatory coordination for deployed AI systems.
Google DeepMind proposes a taxonomy of ten cognitive abilities and a three-stage evaluation protocol combining held-out AI tasks, human baselines and comparisons between performance distributions. It highlights gaps in evaluating learning, metacognition, attention, executive functions and social cognition. The contribution is a framework for designing a broader measurement program.
Play video
This AI Explained video reviews a major AI development through the lens of benchmarks and evaluation evidence. It is useful context for AI engineering, evaluation, governance, and operational risk.