» Tag
language-models
14 postsClaude Opus 5's Odd Behavior: Writing with Ambiguous Input
The odd behavior of Claude Opus 5 when faced with ambiguous inputs was discovered. Important implications for engineers.
BABEL Codec: Fully Opens the Interior of the GPT-2 Model
The BABEL codec translates the internal state of the GPT-2 model into English, achieving 94.7% behavior reconstruction.
Prompt Injection: Threats and Solutions in Engineering
Prompt injection is a structural flaw threatening the security of language models. Solutions for developers are discussed.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comPrevious-Token Prediction Based LLM Near-Exact Prompt Reconstruction
A new approach for prompt reconstruction in LLMs using previous-token prediction is introduced.