Amp

Orbs: Shifting Coding to Cloud — Quinn Slack, Amp Code

Sep 7, 2026 · 40:14

Quinn Slack, CEO of AMP (spun off from SourceGraph), argues mandatory code review and local dev are dead now that agents run remotely in AMP's new Orbs product. Slack says AMP's 20-person trusted team ships fixes 15 minutes after a log or customer report instead of waiting on review, and has stopped using GitHub issues and pull requests, predicting 'the days of CI as we know it are numbered.' He argues cloud sandboxes with time-limited OIDC tokens are more secure than developer laptops, demos agent-built 'apps' replacing settings screens, and previews 'jellyware'—internal tools anyone can remix with their own agent. He recounts spinning AMP off from SourceGraph—rare since Yammer left Geni in 2009—keeping investors in both companies, and staying profitable without hiring PMs or marketers.

Steve Yegge's Vibe Coding Manifesto: Why Claude Code Isn't It & What Comes After the IDE

Dec 26, 2025 · 37:25

Steve Yegge argues that vibe coding—using multi-agent AI workflows—will replace traditional IDEs by January 1, calling anyone still using an IDE a 'bad engineer.' He claims Claude Code, Cursor, and the 2024 stack are already obsolete, predicting agent orchestration dashboards (like his VC project) will manage fleets of agents. Yegge highlights that senior engineers with 12–15 years of experience are the most resistant, but their productivity will be eclipsed by vibe coders. He warns that merging code becomes a new wall as agents produce 10x more code, citing one company's solution of one engineer per repo. Yegge also notes the chaos inside AI labs (OpenAI, Anthropic, Google) as they scale, and believes open‑source models will approach frontier capability within a year.

Amp: The Emperor Has No Clothes

Sep 25, 2025 · 1:21:59

Quinn Slack (CEO) and Thorsten Ball (Amp Dictator) from Sourcegraph discuss Amp Code, a coding agent that ships 15x/day with no code reviews. They explain the strategic pivot from Cody to Amp, emphasizing that building the best coding agent trumps everything else. The team dogfoods Amp internally, using it to build itself, and maintains both a VS Code extension and CLI, with a 50/50 internal split. They argue that model choice is becoming less important than the harness around the model, and they reject features like prompt enhancers, custom subagents, and MCP servers as not adding value. Common failure modes include outsourcing thinking but not typing and using agents without proper context engineering. They predict async agents running 24/7 will dominate, and they target early adopters willing to adapt their codebases and workflows for maximal agent effectiveness.