171–180 of 233 posts
I've just written up a longer form of that comment: "Hallucinations in code are the least dangerous form of LLM mistakes" - https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
Every time this topic comes up I post a similar comment about how hallucinations in code really don't matter because they reveal themselves the second you try to run that code. I've just written up a longer form of that comment: "Hallucinations in code are the least dangerous form of LLM mistakes" - https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
In dynamic languages, runtime errors like calling methods with inexistent arguments etc only manifest when the block of code containing them is run and not all blocks of code are run at every invocation of the programs.
As usual, the defenses against this are extensive unit-test coverage and/or static typing.
Every time this topic comes up I post a similar comment about how hallucinations in code really don't matter because they reveal themselves the second you try to run that code. I've just written up a longer form of that comment: "Hallucinations in code are the least dangerous form of LLM mistakes" - https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
Also there are plenty of mistakes that will compile and give subtle errors, particularly in dynamic languages and those which allow implicit coercion. Javascript comes to mind. The code can easily be runnable but wrong as well (or worse inconsistent and confusing) and this does happen in practice.
Earlier quoted context omitted.
GPT can't even tell what its done or give what it knows it should. It's endless, "Apologies, here is what you actually asked for ..." and again it isn't.
I would love an AI coding assistant that doesn't respond until it's gone out and tested its answer in a sandbox to confirm it actually compiles.
Every time this topic comes up I post a similar comment about how hallucinations in code really don't matter because they reveal themselves the second you try to run that code. I've just written up a longer form of that comment: "Hallucinations in code are the least dangerous form of LLM mistakes" - https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
> because they reveal themselves the second you try to run that code. In dynamic languages, runtime errors like calling methods with inexistent arguments etc only manifest when the block of code containing them is run and not all blocks of code are run at every invocation of the programs. As usual, the defenses against this are extensive unit-test coverage and/or static typing.
Right, that's the exact point I make in my blog post: you have to TEST the code - not just with automated tests, you have to actually try it out yourself as well. https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
Every time this topic comes up I post a similar comment about how hallucinations in code really don't matter because they reveal themselves the second you try to run that code. I've just written up a longer form of that comment: "Hallucinations in code are the least dangerous form of LLM mistakes" - https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
Where the GAI hallucinates an api it is not always easy to find out if it exists given different versions and libraries for a given task, it can easily waste 10 mins trying to find the promised api, particularly when search results also include generated ai answers. Also there are plenty of mistakes that will compile and give subtle errors, particularly in dynamic languages and those which allow implicit coercion. Ja…
Earlier quoted context omitted.
GPT can't even tell what its done or give what it knows it should. It's endless, "Apologies, here is what you actually asked for ..." and again it isn't.
I would love an AI coding assistant that doesn't respond until it's gone out and tested its answer in a sandbox to confirm it actually compiles.
Earlier quoted context omitted.
I've made the opposite observation. Without proper abstractions code bases grow like crazy. At some point they are just a huge amount of copy, paste, and slight modification. The amount of code often grows exponentially. With more lines of code comes more effort to maintain it. After a few years those copy and pasted code pieces completely drift apart and create a lot of similar but different issues, that need to be…
> At some point they are just a huge amount of copy, paste, and slight modification. I mean is that bad? Unless you keep having to have huge MRs that modify every copy/paste could you just let the code sit there and run forever? I only say this because I've been a maintenance programmer and I could only dream of a codebase like this. The idea that I get a Rollbar with a stack trace and the entirety of what the code a…
Every time this topic comes up I post a similar comment about how hallucinations in code really don't matter because they reveal themselves the second you try to run that code. I've just written up a longer form of that comment: "Hallucinations in code are the least dangerous form of LLM mistakes" - https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
Where the GAI hallucinates an api it is not always easy to find out if it exists given different versions and libraries for a given task, it can easily waste 10 mins trying to find the promised api, particularly when search results also include generated ai answers. Also there are plenty of mistakes that will compile and give subtle errors, particularly in dynamic languages and those which allow implicit coercion. Ja…
Every time this topic comes up I post a similar comment about how hallucinations in code really don't matter because they reveal themselves the second you try to run that code. I've just written up a longer form of that comment: "Hallucinations in code are the least dangerous form of LLM mistakes" - https://simonwillison.net/2025/Mar/2/hallucinations-in-code/
Where the GAI hallucinates an api it is not always easy to find out if it exists given different versions and libraries for a given task, it can easily waste 10 mins trying to find the promised api, particularly when search results also include generated ai answers. Also there are plenty of mistakes that will compile and give subtle errors, particularly in dynamic languages and those which allow implicit coercion. Ja…