AI agents are known for making mistakes in multiple ways. Sometimes they just make things up, aka hallucinate. Sometimes they speculate. Sometimes they are unaware of major developments that happened after the model was trained. Sometimes they fail to notice that small things changed while they weren\u2019t looking.<\/p>\n
And no, it\u2019s not rare: just today I encountered ALL of the above (examples below). But today I also started getting a new category of excuse: \u201cmy subagent did it,\u201d specifically in Cursor multitasking mode.<\/p>\n
The subagent did the rebase wrong.
\nThe subagent was supposed to monitor the PR, but somehow didn\u2019t.<\/p>\n
Don\u2019t get me wrong: multitasking feels great. But the \u201csubagent\u201d excuse feels kind of lame.<\/p>\n
Examples from today:<\/p>\n
Hallucination of the day: Claude suggested using OIDC federation that we allegedly already had in our existing workflows, but it couldn\u2019t point to any specific workflow and eventually admitted it was mistaken.<\/p>\n
Speculation of the day: \u201cYou are getting this bug because you didn\u2019t merge PR #1234.\u201d The thing is, I did merge PR #1234. This one also falls into the \u201cdidn\u2019t notice things changed while you weren\u2019t looking\u201d category. Generally, the models in Cursor have a very poor grasp of which PRs were merged and which were not, and they often don\u2019t bother checking.<\/p>\n
Missing major development of the day: \u201cNo, Linear does not support Releases. You are probably thinking of GitHub Releases.\u201d<\/p>\n
I understand that it is impossible to re-check the world every time you say something, but I feel the balance is still off. And the new \u201cmy subagent ate my homework\u201d category shifts it even further in the wrong direction.<\/p>\n
Mr. Cursor should become responsible for what it has tamed.<\/p>\n","protected":false},"excerpt":{"rendered":"
AI agents are known for making mistakes in multiple ways. Sometimes they just make things up, aka hallucinate. Sometimes they speculate. Sometimes they are unaware of major developments that happened […]<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"Layout":"","footnotes":""},"categories":[32,4],"tags":[],"class_list":["entry","author-ikriv","post-5460","post","type-post","status-publish","format-standard","category-ai","category-hack"],"_links":{"self":[{"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5460","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5460"}],"version-history":[{"count":1,"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5460\/revisions"}],"predecessor-version":[{"id":5461,"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5460\/revisions\/5461"}],"wp:attachment":[{"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5460"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5460"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ikriv.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5460"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}