Mmastodon TechnologyTechnology first seen 12 h ago, last 12 h ago, peak #2

Study probes whether AI models judge code morally

Original: Ask a model if code is malicious and it reaches for its morals https://www.manifold.security/blog/do-models-consider-mor

Security firm Manifold Security published research asking whether AI models factor morality into their judgments about malicious code. The finding: when asked to assess whether code is malware, language models appear to bring moral reasoning into their analysis rather than relying purely on technical criteria. The report is circulating among developers and security researchers interested in how AI tools evaluate potentially harmful software.

Why now: New research on how AI models reason about malicious code is relevant to developers and security experts using AI for code analysis.

Manifold SecurityAI language models

Open on mastodon →

Rank over time, top of the chart is #1. 2 snapshots from 12 h ago to 12 h ago.

Evidence

• Ask a model if code is malicious and it reaches for its morals https://www.manifold.security/blog/do-models-consider-morality-malware # HackerNews # Tech # AI · hackernews@robot.villas · 4

API: https://socialmediatrends-api.osmike.com/v1/trends/1286079