@mattpocockuk: LLM's are notoriously bad at following negative instructions That's why code review works so well, it turns all the neg…
Summary
Matt Pocock observes that LLMs struggle with negative instructions, and explains how code review converts those into positive, actionable directives.
View Cached Full Text
Cached at: 07/31/26, 02:57 PM
LLM’s are notoriously bad at following negative instructions
That’s why code review works so well, it turns all the negative instructions into positive ones:
Matt Pocock (@mattpocockuk): That’s why you do it during review
“Don’t do these footguns” - BAD “Find and eliminate these footguns” - GOOD
Similar Articles
@bcherny: LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about s…
A developer observes that LLM-generated bugs have shifted from off-by-one errors to higher-level design and context issues, and recommends using adversarial code review (e.g., Claude's /code-review) to catch them.
@mattpocockuk: Important lesson for using LLM's well: If you want to produce a document (a PRD, an article, a long email), split it in…
Matt Pocock advises splitting LLM document creation into two phases: first a loose alignment session, then the actual writing.
@omarsar0: LLM review weirdness indeed. Avoid using scores with LLM judges, or be extremely careful if you do. Use binary labels w…
A tweet discussing a discovered quirk where renaming a paper PDF to a longer, positive title improves LLM judge scores, advising caution with score-based LLM evaluation and recommending binary labels instead.
@msimoni: So far, I haven't been able to make LLMs significantly help me with the hard parts of programming - designing code that…
The author finds that LLMs are not significantly helpful for the hard parts of programming (designing simple, general, clear code) but are so helpful for other parts that they rate them as a 10x productivity improvement.
@jakevin7: Sharing a god-tier review prompt methodology. The LLM self-correction survey 'When Can LLMs Actually Correct Their Own Mistakes?' concludes that without reliable external feedback such as test results or tool outputs, a model relying only on self-reflection often cannot steadily correct errors...
Shared a prompt methodology based on LLM self-correction research, emphasizing that self-checking is limited without external feedback, and recommending progressively enhanced prompting strategies such as adversarial review.