all the criticism has been said, all the takes been had.
-
So, look. One shot rewriting the whole test suite in another language is probably not great to do, but what happened here is so much worse than you are expecting.
https://github.com/RsyncProject/rsync/pull/903/
This does not "translate tests into pytest" or a unit testing framework, it writes its own testing framework where tests are whole python scripts that redefine basic test functions in every script. Surely there would be a single way to "run rsync and get the results" - nope, well, there is, but then every test file will randomly redefine its own
_run_and_capturefunction. So like now rsync needs a test suite for its test suite.If instead of telling an LLM to "rewrite the tests in python" you just searched "python testing" you would find the pytest docs. And then you would find examples. And then you could write fixtures to deduplicate all the prior shell script setup and teardown stuff, and so on. But since it was just "rewrite the tests in python" its now worse than before, and the odds of the rewrite actually being a 100% faithful translation are close to 0.
I think the modal situation here is that the people are reading none or very little of what is being generated by the LLM, so the tests have a special role: Tests function as the pull arm on the slot machine, you just generate until tests pass, and that's a jackpot. Obviously that's meaningless when the tests are meaningless, so tests take on a very different meaning and role in slot machine coding.
Previously we would write careful test conditions that were based off some real problem or an understanding of what the code under test did, and had a specific thing they were intended to protect against. Tests move slow and are designed to protect us against the things we know can go wrong. When we learn of a new wrong thing, we add a test.
LLM tests have the form of tests but don't do the same thing. They often test nothing, and are just expressions of truisms that the probabilistic text space explored while generating. They have strongly worded names but end up actually asserting that basic language features work as expected. Because it is not us writing tests for ourselves, where we only harm ourselves by making them weak, they function instead as a passively obfuscated justification for the code that the LLM generates. The user wants the tests to pass. The LLM provides.
The tests are theater: they are the play field for the slot machine. They are mild, surmountable, need to fail a few times to be plausible, but must eventually pass within the expected generation loop window to deliver the payout.
-
So, look. One shot rewriting the whole test suite in another language is probably not great to do, but what happened here is so much worse than you are expecting.
https://github.com/RsyncProject/rsync/pull/903/
This does not "translate tests into pytest" or a unit testing framework, it writes its own testing framework where tests are whole python scripts that redefine basic test functions in every script. Surely there would be a single way to "run rsync and get the results" - nope, well, there is, but then every test file will randomly redefine its own
_run_and_capturefunction. So like now rsync needs a test suite for its test suite.If instead of telling an LLM to "rewrite the tests in python" you just searched "python testing" you would find the pytest docs. And then you would find examples. And then you could write fixtures to deduplicate all the prior shell script setup and teardown stuff, and so on. But since it was just "rewrite the tests in python" its now worse than before, and the odds of the rewrite actually being a 100% faithful translation are close to 0.
@jonny@neuromatch.social oh holy FUCK
it is so bad -
I think the modal situation here is that the people are reading none or very little of what is being generated by the LLM, so the tests have a special role: Tests function as the pull arm on the slot machine, you just generate until tests pass, and that's a jackpot. Obviously that's meaningless when the tests are meaningless, so tests take on a very different meaning and role in slot machine coding.
Previously we would write careful test conditions that were based off some real problem or an understanding of what the code under test did, and had a specific thing they were intended to protect against. Tests move slow and are designed to protect us against the things we know can go wrong. When we learn of a new wrong thing, we add a test.
LLM tests have the form of tests but don't do the same thing. They often test nothing, and are just expressions of truisms that the probabilistic text space explored while generating. They have strongly worded names but end up actually asserting that basic language features work as expected. Because it is not us writing tests for ourselves, where we only harm ourselves by making them weak, they function instead as a passively obfuscated justification for the code that the LLM generates. The user wants the tests to pass. The LLM provides.
The tests are theater: they are the play field for the slot machine. They are mild, surmountable, need to fail a few times to be plausible, but must eventually pass within the expected generation loop window to deliver the payout.
@jonny “tests have a special role”
️ -
I think the modal situation here is that the people are reading none or very little of what is being generated by the LLM, so the tests have a special role: Tests function as the pull arm on the slot machine, you just generate until tests pass, and that's a jackpot. Obviously that's meaningless when the tests are meaningless, so tests take on a very different meaning and role in slot machine coding.
Previously we would write careful test conditions that were based off some real problem or an understanding of what the code under test did, and had a specific thing they were intended to protect against. Tests move slow and are designed to protect us against the things we know can go wrong. When we learn of a new wrong thing, we add a test.
LLM tests have the form of tests but don't do the same thing. They often test nothing, and are just expressions of truisms that the probabilistic text space explored while generating. They have strongly worded names but end up actually asserting that basic language features work as expected. Because it is not us writing tests for ourselves, where we only harm ourselves by making them weak, they function instead as a passively obfuscated justification for the code that the LLM generates. The user wants the tests to pass. The LLM provides.
The tests are theater: they are the play field for the slot machine. They are mild, surmountable, need to fail a few times to be plausible, but must eventually pass within the expected generation loop window to deliver the payout.
Here's an example from some code that was thrust at me this week. The rest of the tests try a bit harder to look like tests, but this one is perplexing.
What does it test? The function name suggests its a smoke test. LLMs love to call things smoke tests. That would suggest this would be an early-run test that fails loudly if some basic precondition - like having ffmpeg - fails. Or, I guess we are smoke testing the
ensure_ffmpegfunction? Anyway who knows. However we first check if ffmpeg or ffprobe are present, which is exactly whatensure_ffmpegdoes. If they aren't present, a warning tells us that ffmpeg/ffprobe are required for the video tests, which makes it seem like this should be a parameterizing test that controls which tests are run, which of course it does not do.So the test literally does nothing and cannot possibly fail, but says it does at least two things, because to an LLM something saying it does something is the same thing as it actually doing that thing.
-
RE: https://hails.org/@hailey/116657391001259044
all the criticism has been said, all the takes been had. the only metaphor i have been finding consistently useful for understanding what is happening with people and "AI" is addiction, and specifically gambling addiction.
@jonny
The model is metastatic… -
Here's an example from some code that was thrust at me this week. The rest of the tests try a bit harder to look like tests, but this one is perplexing.
What does it test? The function name suggests its a smoke test. LLMs love to call things smoke tests. That would suggest this would be an early-run test that fails loudly if some basic precondition - like having ffmpeg - fails. Or, I guess we are smoke testing the
ensure_ffmpegfunction? Anyway who knows. However we first check if ffmpeg or ffprobe are present, which is exactly whatensure_ffmpegdoes. If they aren't present, a warning tells us that ffmpeg/ffprobe are required for the video tests, which makes it seem like this should be a parameterizing test that controls which tests are run, which of course it does not do.So the test literally does nothing and cannot possibly fail, but says it does at least two things, because to an LLM something saying it does something is the same thing as it actually doing that thing.
@jonny I have seen this pattern of which you speak when attempting to use LLMs to compare TCP Delayed-ACK implementations between BSD derived code bases. They generated output suggesting semantics that just weren't there, presumably based on how similarly named things were between each fork, but this was not obvious without reading the source for oneself in context. This went doubly for FreeBSD where there are multiple TCP functional blocks ("stacks").
-
Here's an example from some code that was thrust at me this week. The rest of the tests try a bit harder to look like tests, but this one is perplexing.
What does it test? The function name suggests its a smoke test. LLMs love to call things smoke tests. That would suggest this would be an early-run test that fails loudly if some basic precondition - like having ffmpeg - fails. Or, I guess we are smoke testing the
ensure_ffmpegfunction? Anyway who knows. However we first check if ffmpeg or ffprobe are present, which is exactly whatensure_ffmpegdoes. If they aren't present, a warning tells us that ffmpeg/ffprobe are required for the video tests, which makes it seem like this should be a parameterizing test that controls which tests are run, which of course it does not do.So the test literally does nothing and cannot possibly fail, but says it does at least two things, because to an LLM something saying it does something is the same thing as it actually doing that thing.
To a person, the whole purpose of the test is for it to fail when it should. That's an elemental part of writing good tests: they must fail before the patch, or else they provide no protection. We want protection from failure, that is good for us. We need tests to protect us because we can't possibly evaluate all the other parts of a complex system when we try to fix one part of it.
LLM slot machines change what tests mean - of course we still want the code to work good, but if we're not evaluating the code or the tests, then what the slot machine turns them into is just a high score and the jackpot condition. 130 new tests added, that means its good. They pass, that means I win.
The bugfix loop with LLMs defeats the purpose of automated tests and renders it no better than manual testing: you notice a bug, you yell at the LLM to fix it, you keep looking at the specific thing that's broken until its fixed, good robot, ship it. The changes don't have meaningful tests, and nothing else does either, so the slot machine loop repeats, bug->fix->win. Very velocity. Rocket fuel even.
-
RE: https://hails.org/@hailey/116657391001259044
all the criticism has been said, all the takes been had. the only metaphor i have been finding consistently useful for understanding what is happening with people and "AI" is addiction, and specifically gambling addiction.
Huh, yeah, gambling works as a metaphor!
I was going more with ...
"This person came back from the alien ship, they had a grabby thing on their face but it fell off, and now the person is weirdly hungry, and maybe we should worry about what's growing inside them."
-
To a person, the whole purpose of the test is for it to fail when it should. That's an elemental part of writing good tests: they must fail before the patch, or else they provide no protection. We want protection from failure, that is good for us. We need tests to protect us because we can't possibly evaluate all the other parts of a complex system when we try to fix one part of it.
LLM slot machines change what tests mean - of course we still want the code to work good, but if we're not evaluating the code or the tests, then what the slot machine turns them into is just a high score and the jackpot condition. 130 new tests added, that means its good. They pass, that means I win.
The bugfix loop with LLMs defeats the purpose of automated tests and renders it no better than manual testing: you notice a bug, you yell at the LLM to fix it, you keep looking at the specific thing that's broken until its fixed, good robot, ship it. The changes don't have meaningful tests, and nothing else does either, so the slot machine loop repeats, bug->fix->win. Very velocity. Rocket fuel even.
But its not just as simple as "OK if I read the tests I should be fine" because LLM code is often untestable. It writes code with function and class names that make it seem like a something does something, but they might just be flat wrong. Or there is some invisible fallback condition the LLM encountered while generating code and added to just make tests pass, but has entirely different behavior.
If you've watched an LLM generate a project over time, you see it generating its own private language, and ive even seen it reinvent language features like function definitions themselves. Its names form part of an increasingly inaccessible web of meaning that no human can penetrate.
Writing tests requires a kind of "information gap" where you can have enough intuition about what something does, but not how it does it, so you can a) know what it should do, b) make a strong assertion about that expectation, c) without mirroring the internal implementation's limits. That's hard! And really only possible when the foundation, (a) is true. Code must have an articulable purpose in order to be testable, that's tautological, that defines what failure is. But since LLM code increasingly detaches from any kind of stable description or expectation, even if the tests look very rigorous, you can't know if they are just tailored to the specific internal details of its function to eke out a pass, because it's hard to know what it should do anyway.
So really you have to read the test code, the code under test, and also all the other code that might call the code under test. Aka you have to read everything. And rather than reading something that was written to be read, you're wading through a slop swamp. So you can't. It takes more time than just writing it. The erosion of testing is just an intrinsic part of the loop that you can't escape without breaking the spell of the slot machine, and it is what drives the loop.
-
@elebertus
I think bun's rust rewrite is the single largest high profile yeet I have ever seen, if you haven't seen that yet -
But its not just as simple as "OK if I read the tests I should be fine" because LLM code is often untestable. It writes code with function and class names that make it seem like a something does something, but they might just be flat wrong. Or there is some invisible fallback condition the LLM encountered while generating code and added to just make tests pass, but has entirely different behavior.
If you've watched an LLM generate a project over time, you see it generating its own private language, and ive even seen it reinvent language features like function definitions themselves. Its names form part of an increasingly inaccessible web of meaning that no human can penetrate.
Writing tests requires a kind of "information gap" where you can have enough intuition about what something does, but not how it does it, so you can a) know what it should do, b) make a strong assertion about that expectation, c) without mirroring the internal implementation's limits. That's hard! And really only possible when the foundation, (a) is true. Code must have an articulable purpose in order to be testable, that's tautological, that defines what failure is. But since LLM code increasingly detaches from any kind of stable description or expectation, even if the tests look very rigorous, you can't know if they are just tailored to the specific internal details of its function to eke out a pass, because it's hard to know what it should do anyway.
So really you have to read the test code, the code under test, and also all the other code that might call the code under test. Aka you have to read everything. And rather than reading something that was written to be read, you're wading through a slop swamp. So you can't. It takes more time than just writing it. The erosion of testing is just an intrinsic part of the loop that you can't escape without breaking the spell of the slot machine, and it is what drives the loop.
So rsync rewriting all the tests puts the entire project in play. Now the entire protective surface has been sloshed through a layer of probability, so the loop must accelerate. Followup PRs add more carveouts with lengthy LLM justifications that sound perfectly plausible but amount to an erosion of the protective surface. We go from cumulative improvement to a random walk.
-
@elebertus
Ive read so much LLM code at this point, there are still patterns that are present but elude my understanding, but one thing that's clear is that there are foundational flaw categories that are not improved upon by model version and appear in wildly different projects using wildly different models and harnesses. Testing is a big nexus of those flaws. I am not close to what would be a satisfying explanation of the dynamics, but every project suffers fucked testing problems. -
So, look. One shot rewriting the whole test suite in another language is probably not great to do, but what happened here is so much worse than you are expecting.
https://github.com/RsyncProject/rsync/pull/903/
This does not "translate tests into pytest" or a unit testing framework, it writes its own testing framework where tests are whole python scripts that redefine basic test functions in every script. Surely there would be a single way to "run rsync and get the results" - nope, well, there is, but then every test file will randomly redefine its own
_run_and_capturefunction. So like now rsync needs a test suite for its test suite.If instead of telling an LLM to "rewrite the tests in python" you just searched "python testing" you would find the pytest docs. And then you would find examples. And then you could write fixtures to deduplicate all the prior shell script setup and teardown stuff, and so on. But since it was just "rewrite the tests in python" its now worse than before, and the odds of the rewrite actually being a 100% faithful translation are close to 0.
@jonny One thing I love about this and other posts linking to slop on GitHub is that more often than not I flat out can't follow the link because GitHub is not working.
-
Here's an example from some code that was thrust at me this week. The rest of the tests try a bit harder to look like tests, but this one is perplexing.
What does it test? The function name suggests its a smoke test. LLMs love to call things smoke tests. That would suggest this would be an early-run test that fails loudly if some basic precondition - like having ffmpeg - fails. Or, I guess we are smoke testing the
ensure_ffmpegfunction? Anyway who knows. However we first check if ffmpeg or ffprobe are present, which is exactly whatensure_ffmpegdoes. If they aren't present, a warning tells us that ffmpeg/ffprobe are required for the video tests, which makes it seem like this should be a parameterizing test that controls which tests are run, which of course it does not do.So the test literally does nothing and cannot possibly fail, but says it does at least two things, because to an LLM something saying it does something is the same thing as it actually doing that thing.
@jonny I struggle to express how bleak this is.
-
@jonny I struggle to express how bleak this is.
@jonny It's like everyone decided to take a bath in mercury and leaded gasoline.
-
@jonny It's like everyone decided to take a bath in mercury and leaded gasoline.
-
So rsync rewriting all the tests puts the entire project in play. Now the entire protective surface has been sloshed through a layer of probability, so the loop must accelerate. Followup PRs add more carveouts with lengthy LLM justifications that sound perfectly plausible but amount to an erosion of the protective surface. We go from cumulative improvement to a random walk.
@jonny I just lost my beer league hockey championship as the last shooter on a 14 round shoot out. I'm sitting in my driveway reading your thread. I'll need to read it again in the morning.
I don't remember why I followed you originally. But I love this thread.
This whole rsync thing is the most interesting thing that has come out of the ai bubble.
I had a negative feel for rsync after years ago reading a blog criticizing its sloppy design.
Yet I rely on it daily. I have so many questions.
-
@jonny I just lost my beer league hockey championship as the last shooter on a 14 round shoot out. I'm sitting in my driveway reading your thread. I'll need to read it again in the morning.
I don't remember why I followed you originally. But I love this thread.
This whole rsync thing is the most interesting thing that has come out of the ai bubble.
I had a negative feel for rsync after years ago reading a blog criticizing its sloppy design.
Yet I rely on it daily. I have so many questions.
@poleguy
RIP on the shootout, hopefully the other team bought the beer and you got to pinch the other goalies cheek a bit. You'll get em next season -
@poleguy
RIP on the shootout, hopefully the other team bought the beer and you got to pinch the other goalies cheek a bit. You'll get em next season@jonny indeed, that's the right feeling!
We have sponsorship from a brewery, so the locker room beer (and custom jerseys) are "free."
But we sat at the bar with the other team. It is just a game after all.
Both sides had a good time. And we had fans cheering for both sides. And kids crashing the locker room to celebrate despite the loss... We shared our NA options. Can't ask for more.
I'd love to engage more on this thread technically... I have thoughts. Maybe Monday.
-
I think the modal situation here is that the people are reading none or very little of what is being generated by the LLM, so the tests have a special role: Tests function as the pull arm on the slot machine, you just generate until tests pass, and that's a jackpot. Obviously that's meaningless when the tests are meaningless, so tests take on a very different meaning and role in slot machine coding.
Previously we would write careful test conditions that were based off some real problem or an understanding of what the code under test did, and had a specific thing they were intended to protect against. Tests move slow and are designed to protect us against the things we know can go wrong. When we learn of a new wrong thing, we add a test.
LLM tests have the form of tests but don't do the same thing. They often test nothing, and are just expressions of truisms that the probabilistic text space explored while generating. They have strongly worded names but end up actually asserting that basic language features work as expected. Because it is not us writing tests for ourselves, where we only harm ourselves by making them weak, they function instead as a passively obfuscated justification for the code that the LLM generates. The user wants the tests to pass. The LLM provides.
The tests are theater: they are the play field for the slot machine. They are mild, surmountable, need to fail a few times to be plausible, but must eventually pass within the expected generation loop window to deliver the payout.
