AI Code Generation

133 summarised stories about AI Code Generation, each linking back to the original source. Browse all topics →

Key players

OpenAI Codex Anthropic The New Stack Claude Claude Code

Wednesday, 22 July 2026

Models are worse at reviewing their own code

Greptile 2 months ago 16

Greptile researchers tested whether AI code review models catch bugs in code written by other models versus their own code, finding both Claude and GPT detect more bugs in code written by the competing model. Testing on 1,000 PRs with 1,500 verified bugs showed Claude Opus achieved 39% recall on GPT-authored code but only 28% on Claude-authored code, while GPT showed the opposite pattern. The team launched Model Inversion, a feature that routes code reviews to the opposite model based on author detection, leveraging the finding that cross-model reviews outperform same-model reviews.

Read the full story

AI Coding Agents Claude AI Code Generation GPT-5

The case for making your own apps

Platformer 2 months ago 32

Raycast CEO Thomas Paul Mann discussed Glaze, a new AI tool that lets users build custom Mac apps by describing them in plain English, arguing that hyper-personalized software built for individual needs will replace bloated commercial applications. Glaze launched July 1 and has over 3,000 open-source extensions available, with Mann predicting that within three years 30 to 50 percent of Mac software could be self-made. The shift enables users to avoid software compromises where companies add excessive features for growth, instead creating tailored tools that stay focused on specific personal workflows.

Read the full story

Developer Tools AI Code Generation

Every AI story that matters,
in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.