» Tag
llm
536 postsThe Tragic Alley of the LLM: Asymmetry Between Attackers and Defenders
Exploring the asymmetrical dynamics of LLMs: decision-making time for attackers vs defenders.
Skill-Guided Mining and Compilation of LLM Agent Traces
TraceCompiler mines LLM agent traces to create executable workflows with reduced API calls.
AMD-AGI/HyperLoom: An Agentic System for LLM Workload Optimization
ROCm Hyperloom is an agentic system that optimizes LLM workloads on AMD GPUs.
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.comExploring Software Cracking with AI
Exploring the effectiveness of AI in software cracking and analysis.
Measuring Malicious Intermediary Attacks on the LLM Supply Chain
A systematic study examining malicious intermediary attacks on LLM supply chains is presented.
From LLM Inference to Agentic Workloads: Characterization and Implications
Explore how agentic applications are reshaping LLM services and their system behaviors.
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.