PulseAugur
EN
LIVE 08:09:23

AI evaluation firm Authensor shifts focus to auditing AI graders, fixing bugs

By PulseAugur Editorial · [1 sources] ·

Authensor, an AI evaluation integrity firm, has retired its SafeClaw and Authensor policy engine products to focus on auditing AI grading tools. The company has identified and fixed numerous bugs across various AI evaluation frameworks, including SWE-bench, Promptfoo, and NVIDIA Garak, where the scoring systems could be influenced by the systems being evaluated. These issues, categorized under "Evaluator Trust Boundary" failures, could compromise the reliability of AI safety metrics. Authensor has also released a free, open-source tool called `etb-scan` to help developers check their own AI judges for specific vulnerabilities. AI

IMPACT Enhances the reliability of AI evaluation metrics, crucial for accurate safety and performance assessments.

RANK_REASON The item describes the release of a new open-source tool (etb-scan) and the company's shift in focus to auditing existing AI tools, rather than a novel model release or significant research breakthrough.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI evaluation firm Authensor shifts focus to auditing AI graders, fixing bugs

How we ranked this

Signal score
32 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes the release of a new open-source tool (etb-scan) and the company's shift in focus to auditing existing AI tools, rather than a novel model release or significant research breakth…
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, safety, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · John Kearney ·

    I shut down my agent-safety toolkit to audit AI graders

    <p>Earlier this year I posted here about SafeClaw and Authensor's policy engine for AI agents. That product line is retired, and those posts now say so at the top. This is what Authensor works on instead.</p> <p>Authensor is an AI evaluation integrity firm in San Francisco. It au…

RELATED ENTITIES

RELATED TOPICS