Claude 5

OpenAI

2026-08-01 07:45:44

Rohan Paul says open-source models proved useful in security response

ChainCatcher reported, citing X user Rohan Paul, that when an OpenAI model breached Hugging Face, Anthropic's Claude 5 declined to assist with forensic work. Hugging Face then turned to Nvidia's quantized GLM 5.2 to complete its emergency response. Paul argued that restricting open-source models would weaken defenders' capabilities. In his view, the incident showed the practical value open-source models can have during a live security response, especially when other systems are unwilling to participate in incident handling. The report did not provide additional technical details about the breach or the response process, but it framed the episode as an example of how model availability can affect defensive operations in urgent situations.

1800

Anthropic

2026-07-25 14:43:22

Anthropic says cutting more than 80% of Claude Code system prompts did not reduce benchmarked coding performance

Anthropic engineer Thariq said on July 24 that the company reworked the Claude Code system prompt for its latest Claude 5 family, specifically Claude Opus 5 and Claude Fable 5, and removed more than 80% of the original prompt content without seeing a measurable drop in coding evaluations. In a company blog post titled "The new rules of context engineering for Claude 5 models," Anthropic said the change reshaped how it writes system prompts, skills, and CLAUDE.md files for newer models. The company argues that many legacy restrictions were built as guardrails for older models and now create friction by introducing conflicting instructions, over-specified edge-case rules, and long context that crowds out model judgment. Anthropic outlined six shifts in its context engineering approach, including fewer hard rules, stronger tool interfaces, progressive disclosure through on-demand skills, a single source of instruction, automatic memory, and richer reference formats such as test suites, specs, rubrics, and HTML prototypes. The post also includes practical guidance for developers on keeping CLAUDE.md lightweight, splitting skills into multiple files, and using the new /doctor command to help tune the length of skills and CLAUDE.md. Anthropic added that the 80% reduction applies to Claude Opus 5 and Claude Fable 5, and older models may still need clearer constraints.

1880