» Tag
llm
473 postsAI Audit Uncovers Seven Real Bugs in Cloudflare's CIRCL
zkSecurity's AI audit tool found seven real bugs in Cloudflare's CIRCL cryptography library, all now fixed and mostly rewarded via HackerOne.
Don't Let the LLM Speak, Just Probe Its Hidden State
LLMs already encode the answer in hidden states before generating text. A tiny probe turns this into fast, cheap, calibrated zero-shot classifiers without generation.
How context is managed in long-running agentic systems
A look at how Director's Journal, Critic's Review and Timeline mechanisms keep multi-agent security investigation systems coherent over long-running sessions.
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.comSwarm: A New Framework for Multi-Agent Workflows in Swift
Swarm is a multi-agent framework that provides compile-time security with Swift 6.2, offering an alternative to LangChain. It provides type-safe tools and crash recovery.
Does Code Cleanliness Affect Coding Agents?
Research explores the impact of code cleanliness on autonomous coding agents, highlighting its importance for efficiency in AI-driven development.
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems
SparSEEty addresses token extraction attacks on LLM serving systems, achieving high reconstruction accuracy with minimal overhead.
AdaMAST: Adaptive Failure Taxonomies for Enhancing LLM Agents
AdaMAST is a taxonomy system that analyzes and improves LLM agent failures.
Don't Ask an LLM for a Confidence Score
Explore the misconceptions and implications of asking LLMs for confidence scores.
Anatomy of an LLM Judge: The Model Writes, the Judge Measures
Discover how an LLM judge operates and its significance for engineers.
Frontier-class LLM Inference on a Laptop CPU
cpubrrr surpasses llama.cpp on Apple M4 Max CPU for frontier-class LLMs.