grep -r "Code" /news · home›search
grep -rli "Code" /news

Code

Full-text search across 62594 articles. Combine with topic and date filters; results sorted by relevance.

results 62594 page 508/3130 follow RSS for this search
06:58
2025-04-26
gist.github.com
developer-tools

Some notes on AI Agent Rule / Instruction / Context files / etc

Based on the article, there are several emerging standards for guiding AI coding agents, including **AGENTS.md** (an open format for guiding coding agents) and **DESIGN.md** (a specification for describing visual identit…

23:05
2026-08-22
macaiapps.com
ai-products

Show HN: MacAIApps – a directory of AI-powered Mac apps

MacAIApps, a new directory of AI-powered Mac applications, has launched, featuring over 60 tools including Vinaa, an AI chat aggregator, and various transcription, coding, and productivity apps. The directory highlights …

16:48
2026-06-02
latent.space
ai-agents

GitHub's plan for Agents — Kyle Daigle, GitHub

GitHub COO Kyle Daigle detailed how the platform is adapting to a 1,400% surge in code shipped by AI agents in 2026, which is straining infrastructure originally built for human-paced development. Daigle addressed challe…

06:28
2026-06-03
github.com
ai-tools

open-spdd: Design Philosophy

OpenSPDD, an open-source structured prompt tool, was created to address the "control problem" in AI coding where models generate technically correct but misaligned code. The tool targets rework caused by AI adding uninte…

21:55
2026-08-28
dan-blanchard.github.io
artificial-intelligence

Everything Claude Saw: A Transparent Account of the Chardet v7 Rewrite

The maintainer of the Python character encoding detection library chardet, Daniel Blanchard, rewrote the library from scratch with the help of Anthropic's AI assistant Claude, releasing version 7.0.0 under the MIT licens…

18:11
2026-07-09
vuci.ai
large-language-models

We Tested GPT 5.6 Sol Early

Theo and Ben spent $224,700 in tokens on early access to OpenAI's GPT-5.6 Sol model, concluding that reverting to GPT-5.5 was so unpleasant they stopped coding for the day. The model is a strong coding agent, but they re…

16:54
2026-07-15
lesswrong.com
ai-safety

Expanding AI Control from Models to Harnesses

AI control research must expand from models to agent harnesses as frontier labs adopt harnesses with skills, memory, subagents, and external services by 2026, according to a LessWrong analysis. Claude Code and Codex now …

12:30
2026-06-24
andrewjesson.com
ai-agents

When Does Data Help Automated Context Engineering?

Claude Code can improve other AI agents without training data in four of seven tested applications, performing as well as with data. Data helps only where Claude Code's prior knowledge of the task runs out, and the drift…

05:16
2026-07-14
dev.to
artificial-intelligence

Vibe Engineering: Solving Small Cross-Cutting Concerns

A developer recounts their career journey from oil and gas to healthcare and back, culminating in a role at a software company where they now use AI-assisted coding tools to tackle complex codebases. They built a high-en…

08:03
2026-06-05
dev.to
ai-agents

Review Doesn’t Scale, Validation Does

Mike, in collaboration with Anthropic's Claude, argues that code review does not scale to the volume of code produced by AI agents, and that validation must replace it as the primary safeguard. The engineer contends that…

14:07
2026-08-14
a16z.news
artificial-intelligence

Cursor + SpaceXAI: the fastest iterating team wins

Cursor, the AI code editor developed by Anysphere, has been officially acquired by SpaceXAI, according to a16z. The acquisition positions the combined team to dominate the AI coding market, which a16z estimates is only 1…

07:30
2026-06-27
github.com
ai-tools

Gstack

Y Combinator CEO Garry Tan released gstack, an open-source tool that turns Claude Code into a virtual engineering team, enabling him to ship 40+ features in 60 days while running YC full-time. Tan claims his 2026 coding …

18:45
2026-09-10
gilesthomas.com
large-language-models

Extending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090

A developer extended Sebastian Raschka's GPT-2-style code from the book "Build a Large Language Model (from Scratch)" to add mixture-of-experts support and trained a 446M-parameter model with 220M active parameters from …

← prev page 508 / 3130 next →