News

AI, cybersecurity, machine learning, scraping & programming news.

All ai machine learning cybersecurity scraping programming languages technology Important
ai Oct 05 FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution Prior work on LLM-guided evolutionary methods such as AlphaEvolve has demonstrated strong results on computational optimization problems, including circle packing. However, these approaches typically optimize for performance gain... machine learning Oct 05 Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models Masked diffusion language models (dLMs) present a parallel alternative to autoregressive models for complex reasoning, yet they encounter a credit-assignment problem: a few commitments during denoising sharply reduce uncertainty o... ai Oct 04 Show HN: Shlexball, describe a file and a local 1.5B model finds it on your Mac Searching Mac files with plain language Shlexball arrives as a Mac application that lets you find files by describing them in plain English. Instead of remembering exact filenames or digging through folder hierarchies you type wha... cybersecurity Oct 04 Leaving Substack Substack expands Australia’s Online Safety Act across all publications A Hacker News post by GianFabien announced their departure from Substack, citing the platform’s decision to comply with Australia’s Online Safety Act for every... machine learning Oct 04 Full-fabric VHDL LLM inference engine. Runs Qwen3.5-class transformer inference FPGA fabric runs Qwen3.5 at 9B parameters with no GPU in sight A project called llm.vhdl has built a complete large language model inference engine in VHDL that runs on Xilinx Versal FPGAs. The design executes Qwen3.5-class models... programming languages Oct 04 Google froze its open source bug bounty program due to a ‘significant rise’ in AI submissions Google halts open-source bug bounties after AI-generated flood Google has suspended its Open Source Software Vulnerability Rewards Program effective October 1, citing a surge in automated submissions that are largely invalid. The... ai Oct 04 Building a RAG Pipeline for Semantic Code Search Building a RAG Pipeline for Semantic Code Search: A Developer Diary and Field Notes Some time ago, JetBrains set out to build the best semantic code search platform we could: a RAG pipeline that gives LLM agents precise, citable e... ai Oct 04 Show HN: Exro – I got tired of cleaning up copy/paste between apps Building a RAG Pipeline for Semantic Code Search: A Developer Diary and Field Notes Some time ago, JetBrains set out to build the best semantic code search platform we could: a RAG pipeline that gives LLM agents precise, citable e... ai Oct 04 Show HN: Jev-pages – Building landing pages real time with Jev Landing pages that assemble themselves from structured choices A developer named Pranav Sagar built a tool that turns rough product notes into a finished landing page without writing a single word of copy. The project, called jev-... programming languages Oct 04 Docent- An Open Source Private AI assistant in your terminal A terminal-first AI assistant that manages its own runtime Docent is a private AI assistant that runs from the terminal. It chats with your PDFs and Office files, searches the web, and connects MCP servers. If no local agent is ru...