» Tag
natural language processing
2 postsThe Implications of Linguistic Illegibility for LLM Security
Linguistic illegibility in LLMs raises concerns about the reliability of security mechanisms. Taint tracking and other methods are proposed to enhance safety.
Reducing Token Usage Through Representation Engineering
Insights on reducing token usage with the Caveman package and the role of activation steering.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.com