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

Code

Full-text search across 63061 articles. Combine with topic and date filters; results sorted by relevance.

results 63061 page 543/3154 follow RSS for this search
16:11
2026-09-02
dev.to
ai-safety

If your file-guard hook is registered on Read, it never sees cat

A developer found that Claude Code's PreToolUse hooks registered on the Read tool do not fire when file contents are accessed via Bash commands like cat, allowing secrets to reach the model. Testing on Claude Code 2.1.24…

19:34
2026-08-28
github.com
developer-tools

Foremerge

Foremerge 0.4.0, an open-source coordination protocol for coding agents built above Git, lets agents announce their intended changes in a shared SQLite store inside the project's .git folder, detecting semantic collision…

00:00
2026-08-25
digitalapplied.com
ai-policy

What Happens When You Hit Your AI Spend Cap: A Census

A census of eight API vendors and four coding-CLI surfaces found that the dominant documented behavior when hitting an AI spend cap is a hard stop via HTTP 429, 402, or 400, not a graceful degrade, according to vendor do…

20:08
2026-08-19
sourcefeed.dev
artificial-intelligence

AI Agents Fail Off a Cliff Below the Application Layer

A new open catalogue, low-level-skills-trothbyte on GitHub, documents 55+ failures of AI coding agents in assembly, Rust, concurrency, and systems code, backed by independent research, but its proposed fix—a library of '…

14:04
2026-08-17
ai-news.ghost.io
artificial-intelligence

Cursor's new owner is Musk's AI company — a $60 billion deal

SpaceXAI, Elon Musk's AI company formerly known as xAI, closed a $60 billion all-stock deal for Anysphere, the maker of the Cursor coding agent, on August 14, marking the largest startup acquisition on record. Separately…

23:24
2026-08-14
lesswrong.com
artificial-intelligence

Your Agents Are Not Time Aware

Coding agents Claude Code and Codex consistently over-predict their own wall-clock runtime, according to research conducted as part of MATS 10 with Maksym Andriushchenko. The study introduced AgentTime, an evaluation sui…

13:55
2026-08-14
jasonfleetwoodboldt.com
artificial-intelligence

Structure Was Always the Hard Part

Koushik Dasika's post 'Coding Was Never the Hard Part' argues that AI's ability to write code exposes that the real difficulty in software engineering has always been structural decisions, not syntax. The article contend…

04:51
2026-08-10
pub.towardsai.net
artificial-intelligence

Your AI Agent Isn’t Dumb. (How Real AI Engineers Work Daily)

Martin Fowler says context is the bottleneck for coding agents, and a developer's experience shows that inconsistent code stems from ambiguous domain vocabulary, not weak models. In an enterprise NL-to-SQL pipeline, the …

13:12
2026-08-05
blog.calif.io
ai-tools

The WordPress Chain Massacre

SLCyber researchers demonstrated a post-exploitation chain, wp2root, that escalates WordPress core remote code execution to Linux root in under an hour using OpenAI's Codex. The chain exploits a use-after-free in PHP to …

06:59
2026-07-31
dev.to
developer-tools

AI-Assisted Engineering: Faster to Build Isn't Cheaper to Own

A developer argues that AI-assisted coding tools make building software faster but not cheaper to own, citing a small bug in a clean-looking change that passed tests but misread an API response. The developer references …

08:52
2026-07-27
jcs.org
ai-tools

On AI

Developer jcs recounts his evolving relationship with AI-assisted coding, from initial skepticism to adopting Claude Code and local models like Ollama, while maintaining a vintage Macintosh programming hobby that rejects…

← prev page 543 / 3154 next →