Tag
A developer discovers that swapping two equivalent macros caused unexpected integer changes in unrelated functions, and the blog post investigates the mystery, questioning an LLM's explanation about control flow guard.
Arcaide is a tool that builds multi-level call graphs to help developers explore and understand codebases by combining structural and behavioral analysis, using an LLM to enrich the graph and strip out trivial utilities.
This paper proposes token-efficient retrieval methods for LLM analysis of transactional legal documents, demonstrating that structured retrieval can match full-corpus injection in answer quality while using significantly fewer tokens and lower cost.
This paper uses a pre-trained LLM with zero-shot classification to analyze approximately 20 million Twitch chat messages across seven game genres, finding that 2.4% of messages are toxic, with MOBA games having the highest rate (3.2%) and sports games the lowest (2%). The study also identifies significant differences in toxicity distributions across individual games within the same genre.
This article introduces Qwen-Scope, a toolkit of Sparse Autoencoders (SAEs) trained on Qwen3 and Qwen3.5 models to enable mechanistic analysis and intervention. It releases 14 groups of SAE weights covering dense and MoE backbones, providing sparse representations for residual-stream activations.
This academic paper analyzes the syntactic and lexical diversity of two generations of LLMs compared to human-authored news text, finding that newer, aligned models exhibit reduced diversity.
DeepMind releases Gemma Scope 2, an open suite of interpretability tools for the Gemma 3 model family, aiming to help the AI safety community understand and debug complex language model behaviors like hallucinations and jailbreaks.