Building https://xitter.cf/t.co/pRJXNjcrwa. Co-founder and CTO of Watchmouse (acquired by CA Technologies (acquired by Broadcom)).
- Tweets6.3K
- Following1.7K
- Followers1.2K
- Likes14.1K
ALT PubMed is now on Paperzilla
ALT Diagram labeled “Figure 1: The round function Rᵣ of FRAST.” Inputs y₁, y₂, …, y₃₂ flow downward to updated outputs. Branches pass through round-key additions and S_erf blocks; a sum of branches feeds a round-key addition and S_crf block back into the first branch.
ALT Diagram labeled “Figure 1: The round function Rᵣ of FRAST.” Inputs y₁, y₂, …, y₃₂ flow downward to updated outputs. Branches pass through round-key additions and S_erf blocks; a sum of branches feeds a round-key addition and S_crf block back into the first branch.
ALT Diagram of an attacker controlling third-party content accessed by an LLM agent. The agent invokes Skill A, which invokes Skill B, then Skill C. All three skills are marked “Clean,” but their composition leads to a “Violation.” A crossed-out path states “No Skill Modification.”
ALT Diagram of an attacker controlling third-party content accessed by an LLM agent. The agent invokes Skill A, which invokes Skill B, then Skill C. All three skills are marked “Clean,” but their composition leads to a “Violation.” A crossed-out path states “No Skill Modification.”
ALT Diagram of an attacker controlling third-party content accessed by an LLM agent. The agent invokes Skill A, which invokes Skill B, then Skill C. All three skills are marked “Clean,” but their composition leads to a “Violation.” A crossed-out path states “No Skill Modification.”
ALT Flowchart linking incrimination → detection → deterrence. Revealing malicious behavior and detecting unauthorized actions lead to gathering evidence that an agent is dangerous. Detecting and mitigating unauthorized actions and reducing attempted attacks lead to preventing agents from carrying out successful attacks.
ALT Flowchart linking incrimination → detection → deterrence. Revealing malicious behavior and detecting unauthorized actions lead to gathering evidence that an agent is dangerous. Detecting and mitigating unauthorized actions and reducing attempted attacks lead to preventing agents from carrying out successful attacks.
ALT A case from SKILLCLASH. Top: two skills for the same job, with each rule shortened and labeled by its kind (Section 3). Bottom: outputs of Qwen3-4B for the request “Write the commit message: add pagination to the audit log API. Ticket AUD-77. Author: Omar Haddad. Component: audit-api.” Lines are shaded by the skill whose rule they follow (blue for A, orange for B, gray for the shared rule). Left: with both skills loaded, the model follows all six rules of B and only the shared rule of A, in either load order. Right: with one meta-skill written by Claude Opus 5.5 (Section 5), with A as the primary, the output follows all ten achievable rules.
ALT A case from SKILLCLASH. Top: two skills for the same job, with each rule shortened and labeled by its kind (Section 3). Bottom: outputs of Qwen3-4B for the request “Write the commit message: add pagination to the audit log API. Ticket AUD-77. Author: Omar Haddad. Component: audit-api.” Lines are shaded by the skill whose rule they follow (blue for A, orange for B, gray for the shared rule). Left: with both skills loaded, the model follows all six rules of B and only the shared rule of A, in either load order. Right: with one meta-skill written by Claude Opus 5.5 (Section 5), with A as the primary, the output follows all ten achievable rules.
ALT Five conceptual stages of SPRA construction. A shared unit census precedes relation planning and role-specific filling; assembly joins source-linked records and stores external citations separately. Validation checks profile conformance, relation endpoints, and source-link integrity.
