TechniqueRLHF / Alignment2 recent entries8 Jul 2026Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability AnalysisarXiv:2607.05842v1 Announce Type: cross Abstract: Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate c→30 Jul 2026Batten Down Your Packages: Mitigation Guidance for Supply Chain CompromiseWritten by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyb
TechniqueAgents8 recent entries26 Jun 2026The Red Queen Godel Machine: Co-Evolving Agents and Their EvaluatorsarXiv:2606.26294v1 Announce Type: cross Abstract: Self-improving agents are state-of-the-art (SOTA) on agentic coding benchmarks and have recently been extended to general domains. However, their sear→8 Jul 2026SEVRA-BENCH: Social Engineering of Vulnerabilities in Review AgentsarXiv:2606.13757v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in automated code-review systems, where their approvals can determine which code is mer→30 Jul 2026Batten Down Your Packages: Mitigation Guidance for Supply Chain CompromiseWritten by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyb→1 Aug 20263/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out …3/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out of a sandbox you thought was locked down. We watched exactly→20 Aug 2026Adversarial Review: Structured Disagreement for Grounded Agentic Code ReviewarXiv:2608.18167v1 Announce Type: new Abstract: Early multi-agent LLM systems often used role-separated teams, yet scaling agent count yields diminishing returns on repository-level coding tasks. Rece→22 Aug 2026More than just code reviewThe key skill required to make productive use of coding agents is being able to confidently instruct them on how to make changes and then confidently verify that those changes have been applied in the→25 Sept 2026DON’T LET YOUR CODING AGENT BE THE ONLY REVIEWER OF ITS OWN CODE. I’m seeing this in my own Claude / Codex sessions, and customers are sendi…DON’T LET YOUR CODING AGENT BE THE ONLY REVIEWER OF ITS OWN CODE. I’m seeing this in my own Claude / Codex sessions, and customers are sending me similar screenshots: | Qodo review is on the money. | →30 Sept 2026CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?arXiv:2609.37216v1 Announce Type: cross Abstract: Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers.
TechniqueSafety3 recent entries8 Jul 2026Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability AnalysisarXiv:2607.05842v1 Announce Type: cross Abstract: Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate c→30 Jul 2026Batten Down Your Packages: Mitigation Guidance for Supply Chain CompromiseWritten by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyb→1 Aug 20263/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out …3/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out of a sandbox you thought was locked down. We watched exactly