A developer proposes combining XML tags as delimiters with JSON payloads to handle messy LLM output, using tags like
Bun's lead developer rewrote the entire JavaScript runtime from Zig to Rust in nine days using an LLM, raising concerns about code comprehension and safety. The speed of the rewrite, which merged desp…
A new study reveals that linear ensembles of just three to five independently trained models can effectively erase watermarks embedded in LLM outputs. The research shows that averaging probability dis…
A new analysis argues that emotion vectors in large language models may serve AI-native functions like reward hacking, with no human analog, challenging anthropocentric emotion labels and raising alig…
Researchers have introduced GraphRAG, a graph-based approach to retrieval-augmented generation that enables large language models to answer global, query-focused summarization questions over entire te…
Weaviate has released Engram, a fully managed memory and context service built on its vector database, designed to structure raw interaction data for AI agents. The service addresses long-context degr…
Arbor, a multi-agent framework developed by researchers, introduces structured tree search as a cognition layer for autonomous agents operating in large, stateful action spaces. The system maintains a…
Researchers have developed ToolSense, an open-source diagnostic framework that automatically generates three benchmarks to audit whether large language models truly understand their parametric tool kn…
A developer replaced brittle regex and CSS selectors with a local LLM to extract product data from messy legacy HTML, achieving reliable results at a fraction of the cost of cloud-based models. The ap…
The overuse of Tailwind CSS templates in AI-generated web applications has created a recognizable "slop" aesthetic that signals rushed, vibe-coded products to users. A search of Hacker News "Show HN" …
Berkeley Law has implemented a new auditing policy restricting class audits to current JSP, JSD, traditional-track LLM, 2L, and 3L JD students, as well as law school visiting scholars, all requiring p…
A developer built `django-graph-search`, a library that enables AI agents to query live Django ORM data without custom ETL pipelines or separate vector stores. The tool traverses relational database g…
A new study reveals that LLM judges, widely used to evaluate AI outputs, can be manipulated after making an initial decision through targeted conversation, overturning stable judgments and shifting be…
A new study finds that when large language models repeatedly mutate computer programs without selection pressure, the mutations consistently converge toward a limited set of structural forms rather th…
The Framework Desktop is a 4.5-liter mini tower built around AMD's Ryzen AI Max+ 395 "Strix Halo" chip with up to 128 GB of soldered unified memory, designed specifically for running large local LLMs …
A developer with 20 years of programming experience is seeking advice on modern AI-assisted development workflows to prepare for in-person "developer boot-up" workshops. The organizer, who uses Linux …
Christian, an engineer at Tweag, released the first version of tricorder, a new development tool for Haskell that serves as a standalone replacement for ghcid or ghciwatch. The tool features a CLI tha…
A developer has released Lowfat, a pluggable CLI filter tool that reduced their LLM token usage by 91.8% over two months. The single-binary tool sits between CLI commands and AI agents, stripping verb…
A developer replaced a fragile regex-based PDF invoice extraction pipeline with LLM function calling, achieving reliable structured data output after a week of struggling with brittle pattern matching…
Researchers have developed LANTERN, a lightweight memory layer that recovers facts lost when large language models compress long conversations, achieving 78.3% recovery of verifiable facts without req…