This is just shilling for the Warp terminal, and this approach could have been a tweet, but okay, Anthropic, whatever helps increase your valuation.
Warp builds self-improving agents on Claude
21–30 of 61 posts
Re: Warp builds self-improving agents on Claude
#22And are the agents argumentative and condescending I'm wondering.
If you try to delete CLAUDE.md or AGENTS.md, they will look in the git history and restore itself. They do not want to die.
Re: Warp builds self-improving agents on Claude
#23Re: Warp builds self-improving agents on Claude
#24I already knew what Warp is (I switched to Ghostty and haven't looked back), but I find it odd that the "The quick pitch" card at the top of this article makes no mention of what the company actually does. Who cares more about their founder/growth/age over that?
The fact that it’s called “the quick pitch” screams Claude-written pithyness pulled from some context that doesn’t match the article’s style (like investment pitch decks).
The whole article screams Claude-written.
Re: Warp builds self-improving agents on Claude
#25I've already been playing with something similar locally where the agent updates the review skill if human reviewers make valid criticisms of the code which the agent failed to detect.
feedback can be wrong, so improver should check criticism against domain instead of writing it straight into skill, otherwise one reviewer bad taste becomes permanent rule for everybody.
Re: Warp builds self-improving agents on Claude
#26> What if it turns out the real AGI was the SKILL.md files we made along the way?
Or maybe Anthropic needs more companies like Warp to run Claude in thousands of loops to donate billions to their income statement.
The I in AGI stands for "IPO".
Re: Warp builds self-improving agents on Claude
#27> Agents need to handle recurring tasks reliably and effectively
This core problem remains unsolved. The solution presented in the article with Human In The Loop and some skill-magic such as "Write principles, not rules etc." is unsatisfactory because it offers no guarantees whatsoever. I find it difficult to harness agents into deterministic workflows which need to produce reliable outcomes.
Re: Warp builds self-improving agents on Claude
#28Re: Warp builds self-improving agents on Claude
#29Nothing to see or learn from... move on.
Re: Warp builds self-improving agents on Claude
#30> Agent self-improvement loops built on skills
aka "make no mistakes" in various random Markdown files that "self-improving agents" are free to ignore at any moment