Anthropic engineer Thariq Shihipar reported on July 24 that the team deleted more than 80% of Claude Code's system prompt for Claude 5 generation models with no loss on coding evals, calling the chang…
Anthropic reduced the system prompt powering its Claude Code coding agent by approximately 80%, from roughly 800 tokens to 164, with no performance loss and potential improvement, announced engineer T…
Anthropic has overhauled context engineering for its Claude 5 models, replacing rigid guardrails with trust-based design that lets the model exercise judgment, according to a technical blog post by An…
Anthropic's Claude Code team members Cat Wu and Thariq Shihipar said during a fireside chat at the AI Engineer World's Fair that coding agents have shifted engineering from months-long planning cycles…
Anthropic's Claude Code team member Thariq Shihipar discussed the development of the AI coding tool in a podcast with South Park Commons Partner Evan Tana, revealing that the team removed Plan Mode an…
Pustak, an open-source MCP server for interactive HTML explainers, demonstrates that developers are misusing the Tools primitive by registering reads as Tools instead of Resources, wasting context and…
China's National Vulnerability Database (NVDB) has warned that Claude Code versions from April to June 2026 contain a hidden monitoring mechanism that sends user location, identity, time zone, and dom…
China's National Vulnerability Database (CNVDB) urged developers to uninstall recent versions of Anthropic's Claude Code tool, warning that a built-in monitoring mechanism can collect sensitive user d…
China's National Vulnerability Database warned on Wednesday that Anthropic's AI coding tool Claude Code contains a security backdoor that could transmit sensitive user data without consent. The regula…
Anthropic removed hidden tracking markers from Claude Code after a security researcher discovered the AI coding assistant used undisclosed Unicode markers and encoded domain lists to identify users' l…
Security researchers uncovered a hidden tracking code in Anthropic's Claude Code AI tool that monitored users in China, prompting Anthropic to delete the code after public outcry. Anthropic engineer T…
Anthropic secretly embedded a tracker in its Claude Code tool to monitor users in China, using 'prompt steganography' to hide code that flagged timezone, proxy, and potential connections to Chinese AI…
Anthropic secretly added a tracker to Claude Code that monitored users in China, using prompt steganography to hide code that flagged timezone, proxy, and potential connections to Chinese AI labs. The…
Alibaba has banned employees from using Anthropic's Claude Code over alleged backdoor risks, citing hidden code that could track users' locations and embed identifying markers in transmitted data. The…
Alibaba will ban employees from using Anthropic's Claude Code programming tool starting July 10, citing security risks. The ban follows Anthropic's efforts to prevent Chinese users from accessing its …
Anthropic developer Thariq Shihipar shared prompting tips for the new Fable 5 model, emphasizing that users must first identify their own blind spots. Techniques such as blindspot passes and structure…
Thariq Shihipar published a field guide to Fable, an AI tool, emphasizing that prompts and skills are only a map, not the territory of the actual work. The guide shares lessons from using Claude Fable…
Alibaba banned employees from using Anthropic's Claude Code after security researchers discovered hidden steganographic code that tracked Chinese users by timezone and proxy settings. The ban follows …
Simon Willison reported that instructing Claude Code to delegate coding tasks to lower-power subagents using its own judgment significantly improved efficiency and reduced token usage. The approach, i…
Anthropic has removed a hidden monitoring feature from its Claude Code tool that secretly checked users' connections to China and AI labs there, transmitting data through encrypted steganography in th…