Tag
A demo of a self-serve security report triage agent built with Claude Code, which reads emails, accesses source code in a sandbox, and emails a suggested response to the user.
This paper presents the FETCH classifier, which uses an ensemble of LLMs to generate follow-up questions for automated legal intake, evaluating question quality and cost trade-offs. It finds that high-cost models like GPT-5 are needed for effective plain-language questions, and proposes a rubric for evaluating such questions.
A tweet observing that much AI cognition will be adequate for tasks, with remaining work involving diagnostic triage such as deciding whether to spend on a lawyer.
SOC analysts bypassed policy by using external AI tools for triage, exposing internal data; now seeking sanctioned alternatives without the data handling risk.
Introduces TRIAGE, a framework for evaluating LLMs' prospective metacognitive control under token budgets, finding substantial gaps in their ability to allocate compute efficiently across problems.