banteg (@bantg): claude code appears significantly better than any of the vscode forks. anthropic really killed them all with a cute tui.
Estimated coin impact
Scores are not price-change percentages. High impact means a score of +70 or more, or -70 or less.
Impact unavailable
claude code appears significantly better than any of the vscode forks. anthropic really killed them all with a cute tui. claude wins in planning and perseverance. it can iterate on failing tests for 10 tries without your input, as can it write one off scripts when it needs to learn how your code works at runtime to continue. all of that unprompted. the inference cost is about $20/hour, but i still suggest trying it. it's the first time an ai agent has true agency and feels like an actual collaborator.