OKay, so, it has become very popular to cowrite code with a LLM. And I cannot argue that it is a tremendous force multiplier, however, I do have some suggestions<\/p>\n
#1) Painful as it might be, *read every diff*. Do not ever commit code you haven’t read.
\n a) While you’re reading, see if you can shorten the comments. LLMs overcomment – the reason this matters is if you are going to use
\n LLMs to maintain the code over long terms, you do *not* want to be burning tokens with excessive comments<\/p>\n
b) Check the logic and approach. LLMs make mistakes. <\/p>\n
#2) If the LLM says something improbable, *definitely* push back. *Expect* the LLM to draw incorrect conclusions from individual failures – one example, recently Claude concluded that the shopify metaobject filter didn’t work because you can only create a metaobject filter for a metaobject
\nwhich exists. It didn’t know that, got errors, and concluded the errors were fatal in scope to the operation. It was all set to create a implementation with 30 webhook registrations where only 3 were needed. I repeatedly pushed back, and led it down the correct road, until it understood the right way to do things.<\/p>\n
#3) Point out when the LLM says something blatantly wrong. among other things, there isn’t any real reasoning going on – remember, LLMs have no aboutness, they’re in no way anchored in reality – they can’t tell a cat from a cow, they just are a sliding set of activations of weights moving through a transformer, also thought of as a feed-forward ANN with a attention head. By pointing out a blatently wrong statement, you may well nudge them into the correct alignment.<\/p>\n
#4) *TEST* everything. One *good* thing about LLMs is they are wonderful at writing unit tests. Use this ability – but also end to end test the system under development unless you can tell by reading the code that it’s going to work – and maybe even then. Certainly don’t release anything to production that hasn’t been tested. <\/p>\n
#5) Sometimes, write it yourself. You need to keep the ability to write code, and it will atrophy if you don’t use it. You want to occasionally exercise those pathways – neural skills are use it or lose it.<\/p>\n","protected":false},"excerpt":{"rendered":"
OKay, so, it has become very popular to cowrite code with a LLM. And I cannot argue that it is a tremendous force multiplier, however, I do have some suggestions #1) Painful as it might be, *read every diff*. Do not ever commit code you haven’t read. a) While you’re reading, see if you can […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-4880","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/posts\/4880","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/comments?post=4880"}],"version-history":[{"count":1,"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/posts\/4880\/revisions"}],"predecessor-version":[{"id":4881,"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/posts\/4880\/revisions\/4881"}],"wp:attachment":[{"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/media?parent=4880"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/categories?post=4880"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.sheer.us\/weblogs\/wp-json\/wp\/v2\/tags?post=4880"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}