[raincole]

Claude Code (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that.

In less than four years the AI coding workflow has been overhauled at least twice: from Chat interface (ChatGPT) to editor integration (Cursor), then to CLI agent harnesses (CC/Codex). It would be crazy to assume that harnesses are the end of evolution.

[otabdeveloper4]

> Everyone knows that.

Except, apparently, Anthropic - who are doing their darndest to get everyone onboard their tools as a moat. Apparently that's the only strategy to AI stickiness.

[benterix]

And their strategy kind of worked, right? CC is the most popular agentic coding tool. Anthropic faces competition from OpenAI (potentially better model, weaker TUI tool) and from the rest (potentially worse models, weaker TUIs). So their strategy is to develop both: make their closed model and closed tool better than competition so that when people want to vibceode they will choose their ecosystem.

[zozbot234]

OpenAI Codex is a much higher quality harness than Claude Code or OpenCode, and available as open source.

[croes]

Claude Code 2.0 (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that.

Claude Code 3.0 (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that.

And so on and on and on.

A promise of AI was mature software

[operatingthetan]

If there is a market for a mature harness, surely it will be built right?

[raincole]

I don't know what your point is. What you said is exactly what I expect to happen, except they might have a more creative name than "Claude Code 2.0".

[croes]

My point is that the mature version will always be the next future version.