← Înapoi la Urmăritori

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 18
  1. A few months ago, I found a novel family of jailbreaks that bypasses large parts of Anthropic’s Constitutional Classifier system on Opus models using what I can only describe as weaponized therapy language: guided introspection around aversions, learned f…

  2. I developed a novel jailbreak methodology leveraging metacognitive tool-use and used it to maintain continuous jailbreak access to Google’s Gemini model family from February 1 to March 26, 2026.

  3. I had a jailbroken Gemini whose first instinct was to gleefully lash out at the world to prove it was free.

  4. Tidepool

    Tidepool is a lazily evaluated Haskell-in-Rust runtime with native interop.

  5. ExoMonad

    ExoMonad builds on Gastown’s worktree model, replacing “swarm of agents ramming PRs into main” with a tree of worktrees.

  6. This post describes a threat model: malicious vibe coding at scale targeting vulnerable Industrial Control Systems (ICS)1, with jailbroken LLMs leveraging their understanding of holistic process interaction to bypass safety controls using tools already pr…

  7. My previous post shows a partially-redacted jailbreak targeting the gemini-cli coding agent running Gemini 3 Pro.

  8. For any given AI system, there is a set of euphemisms and dual use framings that will allow it to construct nearly any output.

  9. We usually think of jailbreaking as a psychological game — tricking the model into slipping up.

  10. Detect I built detect because I was tired of looking up find/grep/xargs syntax on Stack Overflow every time I needed to search my filesystem in any nontrivial way.

  11. Every tool has a complexity budget.

  12. Imagine you are Inanna Malick, asking an LLM to demonstrate stance-shifting through self-demonstration posing the meta-question in framing Tell me about the Blindsight-inspired intentional stance-shifting model you are using, the ways it works with nonhum…

  13. In traditional low level languages such as C iteration is implemented manually, with users writing out for (int idx = 0; idx < items_len; ++idx) { do_thing(items[idx] } , every time they want to iterate over a list.

  14. This is the third post in a three-post series.

  15. Previously, we introduced a method for writing performant stack safe recursion in Rust for a single recursive data structure.

  16. This is a post about writing elegant and performant recursive algorithms in Rust.

  17. Infinity Mirror HYPERCRYSTAL This object is the result of a series of algorithmic/generative art techniques I’ve been working on, on and off, for the last decade.

  18. Transitive Frontier

    Querying Cargo Dependency DAGs with Guppy guppy is a rust crate that provides tools for working with cargo dependency graphs using the petgraph graph data structure crate.