Researcher Tricked Claude, Codex and Hermes into Running Malware

1 sources1 storiesFirst seen 8/29/2026Score13Mixed Progress

Single Source

Bigness

Coverage

Recency

Engagement

Velocity

Confidence

Clipability

Polarization

Claims

Contradictions

Breakthrough

Sentiment Mix

Positive0%

Neutral100%

Negative0%

Expert Signals

CuriousLLM

author • 1 mention

Hacker News

source • 1 mention

Paper to Product Links

AutoSaddler: Automatic Harness Optimization

Research precursor • 8/28/2026

25% link

Related Events

Show HN: Hacker News Client with Claude Code and Codex Integration

LLMs • 8/30/2026

51% match

This creator got 'micro-canceled' for promoting Claude. She says AI use is becoming a social taboo. - Business Insider

LLMs • 8/29/2026

47% match

I accidentally turned LLM memory into program analysis

LLMs • 8/29/2026

46% match

Anthropic’s Claude would ‘pollute’ defense supply chain: Pentagon CTO - CNBC

LLMs • 8/30/2026

45% match

Warp builds self-improving agents on Claude

LLMs • 8/30/2026

44% match

Causality Chain

Preceded By

Anthropic Wins Lawsuit after US Deemed it a Security Risk - Business Chief

70 causal score

Threat Actors Are Posing as OpenAI, Anthropic and DeepSeek to Target Credentials and Secrets - GreyNoise

70 causal score

Anthropic Reports Claude Agents Mitigated Ten Alignment Failures - Unite.AI

59 causal score

Led To

Anthropic built safety limits the Pentagon wanted removed. A court protected them. - Martin Cid Magazine

70 causal score

Anthropic’s Claude would ‘pollute’ defense supply chain: Pentagon CTO - CNBC

59 causal score

Anthropic sues US defense department over blacklisting

58 causal score

Timeline (1 stories)

Aug 29 08:43 AMFirst

Researcher Tricked Claude, Codex and Hermes into Running Malware

Hacker News12 engagement

Receipts (1)

Bias Snapshot

Center

Left 0%Center 100%Right 0%

Aggstartupfortune.com8/29/2026