News
AI, cybersecurity, machine learning, scraping & programming news.
Show HN: Local audit trail for Claude Code tool calls
Claude Code runs tools on your machine, shell commands, file edits, network fetches. When the session ends, the terminal is gone and so is the record of what happened. Toolog captures every tool call, stores it in an embedded data...
What are you willing to spend 2 hours on?
A developer on Hacker News is describing a tension that comes with having less time and more experience: the more selective you become about how you spend your hours, the less room you leave for the unplanned discoveries that prod...
GPT-6 Astra is now available in Perplexity Computer
Perplexity has added GPT-6 Astra to its Computer product, making OpenAI's latest model available to Pro and Max subscribers for tasks that require web browsing, file interaction, and multi-step reasoning. What the benchmark shows...
Ask HN: I just learned of the term "Recall@K" – tell me more please?
A developer on Hacker News is asking about Recall@K, a metric that has become increasingly relevant as retrieval systems power more AI applications. The question, and the desire for human input rather than LLM-generated explanatio...
Ask HN: How safe are our password managers in face of LLM cyber attacks?
A developer on Hacker News is asking a question that should worry anyone who stores passwords in a digital vault: if language models can attack systems with unlimited patience and iteration, how safe are password managers against...
Ask HN: (Why) Was the LLM breakthrough useful for images, audio, etc.?
A developer on Hacker News is asking a question that cuts to the heart of why the AI boom has produced advances across so many domains simultaneously: if large language models process text, why did their breakthrough also unlock p...
Cutting (Claude Code) token spend on dynamic workflows 80%
A developer running dynamic workflows with Claude Code has documented an approach that cut token spending by 80% and reduced workflow execution time from five or six hours to twenty or forty minutes. The method works by standardiz...
Show HN: Local 3D LLM Sandbox a tiny assistant with an attitude
A developer has built a local 3D sandbox where a tiny robot with a big attitude builds whatever you ask for, entirely on your machine, with no cloud services involved. The project, llm-sandbox, splits interaction by speed: your ha...
Building a new programming language – looking for contributors
A new programming language called Shaft is attempting to match Rust's safety guarantees while remaining more readable and easier to use. The project is at an early stage, with a C++ and LLVM bootstrap compiler and a self-hosted co...
Bespoke: A Programming Language for People Who Say Please
Programming has developed an unfortunate tone. We kill processes, abort transactions, throw exceptions, break out of loops, and execute instructions. We acquire locks without asking, mutate values without apologizing, and order th...