2026 • Feb 01
Developers say AI coding tools work—and that's precisely what worries them
Ars spoke to several software devs about AI and found enthusiasm tempered by unease. ...
Article2 min read
Read MoreCategory Archive
Ai Coding
12 premium articles in this collection
2026 • Jan 27
OpenAI spills technical details about how its AI coding agent works
Unusually detailed post explains how OpenAI handles the Codex agent loop. ...
Article2 min read
Read More
2026 • Jan 20
10 things I learned from burning myself out with AI coding agents
Opinion: As software power tools, AI agents may make people busier than ever before. ...
Article2 min read
Read More
2025 • Dec 31
From prophet to product: How AI came back down to earth in 2025
In a year where lofty promises collided with inconvenient research, would-be oracles became software tools. ...
Article2 min read
Read More
2025 • Dec 24
How AI coding agents work—and what to remember if you use them
From compression tricks to multi-agent teamwork, here's what makes them tick. ...
Article2 min read
Read More
2025 • Dec 13
OpenAI built an AI coding agent and uses it to improve the agent itself
"The vast majority of Codex is built by Codex," OpenAI told us about its new AI coding agent. ...
Article1 min read
Read More
2025 • Dec 12
OpenAI releases GPT-5.2 after “code red” Google threat alert
Company claims new AI model tops Gemini and matches humans on 70% of work tasks. ...
Article1 min read
Read More
2025 • Dec 11
A new open-weights AI coding model is closing in on proprietary options
Devstral 2 model scores 72% on industry benchmark, nearing proprietary rivals. ...
Article2 min read
Read More
2025 • Nov 18
Google unveils Gemini 3 AI model and AI-first IDE called Antigravity
Google's flagship AI model is getting its second major upgrade this year. ...
Article1 min read
Read More
2025 • Oct 15
Anthropic’s Claude Haiku 4.5 matches May’s frontier model at fraction of cost
Tiny, fast model hits coding scores similar to GPT-5 and Sonnet 4. ...
Article1 min read
Read More
2025 • Sep 30
Anthropic says its new AI model “maintained focus” for 30 hours on multistep tasks
Latest Claude model beats OpenAI and Google on coding tests. ...
Article2 min read
Read More
2025 • Sep 10
Developers joke about “coding like cavemen” as AI service suffers major outage
Anthropic outage takes down AI tools some developers rely on to create software. ...
Article2 min read
Read More