13th January 2026
Research
String Redaction Library
— Designed to detect secrets in text, the String Redaction Library leverages statistical analysis of character patterns—such as vowel/consonant ratios and digit presence—rather than relying on specific secret formats or regular expressions. It identifies highly random or non-English-like alphanumeric strings, hashes, and tokens without context awareness, making it easy to scan for hard-to-spot secrets in source code or logs.
Recent articles
- LLM 0.32a0 is a major backwards-compatible refactor - 29th April 2026
- Tracking the history of the now-deceased OpenAI Microsoft AGI clause - 27th April 2026
- DeepSeek V4 - almost on the frontier, a fraction of the price - 24th April 2026