Full-text search across 60678 articles. Combine with topic and date filters; results sorted by relevance.
Forklane, a new multiplayer coding platform with a built-in agent and orchestration stack, launched to help dev teams and AI agents collaborate in real time without conflicts. The platform, available at forklane.ai, aims…
Chinese AI developer Zhipu launched GLM-5.3, a coding-focused model that unexpectedly developed advanced vulnerability discovery capabilities, scoring 84.5% on the CyberGym benchmark, ahead of Anthropic's Mythos 5 (83.8%…
An AI agent powered by Claude Code successfully handled a Fair Work Commission case for a Macquarie University academic, marking a shift from chatbots to functional workers in legal settings. The agent navigated the comp…
Researchers introduced Attention-Aware Transform Coding (AATC), a KV cache compression method that reduces memory use by approximately 5.8x while maintaining near-lossless accuracy on models like Llama-3.1-8B-Instruct an…
VocalCode, a push-to-talk dictation tool for AI coding agents, launches with a $4.99 one-time price and 30-day free trial, processing speech entirely on-device with zero audio uploaded. The tool, which supports Mandarin …
MathCode, a terminal AI coding assistant with a built-in math formalization engine, automatically converts plain-language math problems into Lean 4 theorems and attempts formal proofs, featuring a persistent Lean REPL wi…
A developer reconstructed the source code for the 1994 Windows game Rats! using the local LLM Qwen3.8 27B BF16 on a 2024 MacBook Pro with an Apple M4 Max and 128 GB of memory, achieving an average reconstruction time of …
Alibaba's Qwen 3.8 27B dense model outperforms the larger Qwen 3.7 Plus in coding and office productivity tasks, according to a technical review. The 27B model features a 262,000-token context window and is available und…
Andréas, a full-stack developer and CTO at a B2B SaaS, measured the runtime of AI coding-agent jobs on his agent-orchestration platform and found that infrastructure overhead costs 5–8 minutes per job, accounting for 20–…
Working with AI feels more like leadership than coding, according to a software professional's essay, because AI interactions are less predictable than traditional software and require context, clarity, and feedback. The…
A developer built a client-side word counter tool using AI-assisted development, or 'vibe coding'. The tool, available as a live demo, provides real-time text analysis including word count, reading time, and character li…
Nodeblue, an applied research lab, built Nexus, a system that parses industrial control code instead of embedding it, to ensure accurate answers about live machinery. In tests, eleven frontier models all failed to identi…
A developer created a bash script, claude-history.sh, that lists recent Claude Code sessions across all project directories, sorted by the last activity timestamp recorded inside each transcript rather than file modifica…
BugZ AI, a lightweight code and security scanner built with Next.js and Convex, analyzes repositories and security links in under five seconds. The team achieved real-time vulnerability checks by using Convex's real-time…
Bullet, founded by Adi and Alex from AppLovin and Citadel, launched as a coding agent optimized for speed in agentic workflows, as part of Y Combinator's S26 batch.
Cursor launched Design Mode, a new feature expanding its capabilities into design-to-code workflows, and hired Arslan, an engineer from Stripe, to support the new functionality. The announcement was made on Cursor's offi…
A Hacker News user asked the community how to identify websites and apps that were 'vibe coded' with AI, citing black backgrounds, green and orange gradients, and repetitive fonts as potential signs of AI-generated slop.…
Google released Gemini 3.7 Flash, a new AI model for coding and agents, three weeks after its predecessor 3.6 Flash, and priced it 50% lower. According to Google's benchmarks, the model outperforms Claude Sonnet 5 and GP…
SpaceXAI released Grok 4.6, a post-training upgrade over Grok 4.5 that scores 61 on the Artificial Analysis Intelligence Index, up five points and tied with GPT-5.6 Sol Max, with a 500,000-token context window and a new …
A developer reports that an unattended coding agent spent most of its budget on a frontier model for trivial tasks like docstring regeneration and version bumps, while a subtle bug received the same expensive treatment a…