News AI

Latest news about AI-assisted development, Burdee updates, and industry insights.

RSS
Human Approval Is the Control Plane
30/08/2026

Human Approval Is the Control Plane

The best agentic workflow is boring on purposeThe most useful AI-assisted development workflows are not the fl…

OpenCode, the terminal agent that speeds up senior engineering work
29/08/2026

OpenCode, the terminal agent that speeds up senior engineering work

Why terminal agents matter nowSenior engineers do not usually lose time because they cannot type fast enough. …

Coding Evaluations Need Human Judgment
29/08/2026

Coding Evaluations Need Human Judgment

When a benchmark becomes a product decisionEvaluation is not a side quest in AI-assisted development. It is th…

When AI Debugs, Humans Must Stay in Control
28/08/2026

When AI Debugs, Humans Must Stay in Control

AI debugging is not AI diagnosisThe appeal of coding agents is obvious when a bug is blocking a team: they rea…

MCP Needs a Human at the Controls
27/08/2026

MCP Needs a Human at the Controls

Every new MCP server is a new permission boundaryThe appeal of MCP is easy to understand: a model that can rea…

Reviewing Agent PRs Without Giving Up Human Judgment
26/08/2026

Reviewing Agent PRs Without Giving Up Human Judgment

Review is now the scarce skillAgents made code cheaper to produce, and review became the new bottleneck. GitHu…

Keep Coding Agents Under Control
25/08/2026

Keep Coding Agents Under Control

Bounded autonomy is the real upgradeThe fastest way to make an AI coding agent useful is not to let it do ever…

The After-Code Gap: Why Humans Still Need to Own AI Output
24/08/2026

The After-Code Gap: Why Humans Still Need to Own AI Output

The after-code gap is where AI still needs humans AI coding tools are getting good at the part everyone can se…

Why Coding Agents Still Need a Human in Control
24/08/2026

Why Coding Agents Still Need a Human in Control

Coding agents are hereCoding agents have crossed a threshold: they are no longer just autocomplete helpers. Th…

Anthropic’s Mythos update shows AI coding is moving from autocomplete to security infrastructure
26/05/2026

Anthropic’s Mythos update shows AI coding is moving from autocomplete to security infrastructure

Anthropic’s latest Project Glasswing update is a useful snapshot of where AI-assisted development is headed ne…

ClickHouse says a year of AI coding agents paid off on a massive C++ codebase
25/05/2026

ClickHouse says a year of AI coding agents paid off on a massive C++ codebase

ClickHouse says the AI-coding-agent hype is starting to meet the realities of a large production codebase. In…

GitHub’s remote Copilot CLI push shows AI coding is becoming a cross-device workflow
24/05/2026

GitHub’s remote Copilot CLI push shows AI coding is becoming a cross-device workflow

GitHub is making Copilot CLI feel less like a one-off terminal helper and more like a shared workspace. In a c…

Google I/O 2026 shows AI-assisted development is shifting from prompts to production
23/05/2026

Google I/O 2026 shows AI-assisted development is shifting from prompts to production

Google used I/O 2026 to make a clear argument: the next wave of AI-assisted development is no longer about wri…

23/05/2026

GitHub's latest Gartner ranking shows enterprise AI coding is becoming a platform race

GitHub's latest Gartner recognition is a sign that AI coding tools are becoming enterprise infrastructure.…

Modal’s $355M raise shows AI coding is becoming an infrastructure business
22/05/2026

Modal’s $355M raise shows AI coding is becoming an infrastructure business

Modal's new Series C is more than another big funding headline. The company says it raised $355 million at a $…

AWS pushes Kiro toward spec-driven AI coding with parallel execution and requirements analysis
19/05/2026

AWS pushes Kiro toward spec-driven AI coding with parallel execution and requirements analysis

AWS is pushing Kiro, its agentic coding tool, in a direction that feels bigger than a feature refresh. The com…