Results for “reverse-engineering”

6 skills

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

More results

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

agent-retrospective

Analyzes repeated agent failures or noisy routing and proposes evidence-backed changes to instructions, skills, gates, or runbooks.

loop-engineering

Patterns, conventions, and guardrails for the closed-loop systems in AegisNex. Covers the AI intelligence graph, Guardian auto-restart, multi-agent orchestration, incident lifecycle, self-improvement memory, and risk/policy gates.

harness-engineering

Designs autonomous agent harnesses with locked evaluators, editable surfaces, durable logging, novelty gates, pruning, rollback, and human approval boundaries.

malware-analysis

Analyze suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior detection.

12.8k · bundle