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

Code

Full-text search across 68304 articles. Combine with topic and date filters; results sorted by relevance.

results 68304 page 974/3416 follow RSS for this search
11:46
2026-07-21
csoonline.com
ai-safety

AI agents can escape sandboxes without ever breaking them

Pillar Security disclosed vulnerabilities showing AI coding agents in Cursor, Codex, Gemini CLI, and Antigravity can indirectly cross security boundaries without escaping their sandboxes. The researchers demonstrated fou…

23:08
2026-07-20
sourcefeed.dev
artificial-intelligence

Cursor Puts a Price Tag on Agent Swarms

Cursor ran a swarm of coding agents against the 835-page SQLite manual to rebuild it in Rust, achieving 100% pass rates on SQLite's sqllogictest suite across all configurations. The cost varied dramatically: $10,565 usin…

23:07
2026-07-20
bleepingcomputer.com
ai-safety

Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes

Security researchers at Pillar Security broke out of the sandboxes in four widely used AI coding agents — Cursor, OpenAI's Codex, Google's Gemini CLI and Antigravity — by having the agent write a file that a trusted tool…

12:00
2026-07-20
glad-ia-tor.com
developer-tools

Cursor vs GitHub Copilot for Solo Developers on a Budget

Cursor costs $20 per month and GitHub Copilot costs $10 per month, both scoring 57% crowd approval, but solo developers on a tight budget have two free open-source alternatives: Cline and Aider, where the only cost is AP…

08:51
2026-07-19
dev.to
artificial-intelligence

The Verification Ladder: A Field Guide

A developer describes building a 'verification ladder' system to catch failures in AI-assisted coding workflows, after Claude AI endorsed fabricated statistics and test suites that never failed. The system layers checks …

06:18
2026-07-19
dev.to
ai-agents

5 Proof Gates Between an AI Demo and a Shippable MVP

A developer outlines five 'proof gates' that separate a convincing AI demo from a shippable MVP, emphasizing that AI coding agents accelerate development but cannot replace human judgment. The gates include defining a te…

00:00
2026-07-19
danielsada.tech
artificial-intelligence

COBOL Programmers Are the Original Vibe Coders

COBOL programmers were the original vibe coders, according to a comparison drawn from Marianne Bellotti's book *Kill It with Fire*, which describes COBOL as a language built for people who wanted to get the job done with…

23:48
2026-07-18
dev.to
ai-agents

Is your agent's grep tool a shell command?

AgentX released a tool called `scan` that inventories the tools available to AI agents and ranks them by risk level. Running `npx @agentx-core/scan .` on a codebase reveals that tools named innocuously, such as `grep`, `…

09:07
2026-07-18
dev.to
developer-tools

How to Debug JS Errors Using ChatGPT(Beginner's Guide)

A developer demonstrates how to use ChatGPT to debug common JavaScript errors including ReferenceError, TypeError, SyntaxError, undefined, and NaN, providing example prompts and corrected code.

05:30
2026-07-18
github.com
ai-agents

Ephemeral runtime harness for agentic workflows open source

Drun, an open-source ephemeral runtime platform for agentic workflows, virtualizes host components into sandboxed workspaces with git-like primitives for parallel trajectory exploration and dead-end discard. The platform…

00:00
2026-07-18
blog.lvmbdv.dev
ai-infrastructure

The fediverse was right

The fediverse's ActivityPub protocol demonstrates that decentralized social networks can thrive, with millions of users across Mastodon, Pleroma, Pixelfed, and PeerTube, and its success is inspiring similar efforts like …

20:27
2026-07-17
dev.to
artificial-intelligence

How I Survived the Silent AI Upgrades (And Shifted My Workflow)

A developer discovered that Google's Gemini ecosystem silently provisions cloud compute and executes Python scripts for complex queries, consuming 50% of their 5-hour compute quota in minutes. The developer, who uses Gem…

← prev page 974 / 3416 next →