| ▲ | verdverm 7 hours ago |
| Sounds kind of like Claude was "cheating" and the humans are engaged in eyes-free coding. Diff so big github refuses to render. I suspect they are reaching the limits of what this new vibe "paradigm" of programming can do. If you haven't pushed a vibe project far, eventually progress becomes near impossible because the slop has grown and the conditions are overly complex, locally focused. Ai is not good at writing reusable software (on their own). stay in the loop friends |
|
| ▲ | parasti 5 hours ago | parent | next [-] |
| To be fair Github refuses to render diffs after a couple of hundred lines. |
| |
| ▲ | verdverm 5 hours ago | parent [-] | | The prior (2nd) commit with ~1700 files at least shows the file tree and such a warning, the latest (3rd) commit is something so big, GitHub will not even do that. |
|
|
| ▲ | thatsabadlook 7 hours ago | parent | prev | next [-] |
| Yup. These are people who have gone full Claude. The dopamine seeking is at previously unseen levels. they think this pr is some factual item that means something so they post it on HN as click bait. But no it only means something to a fulltime ai slopper |
| |
| ▲ | ModernMech 2 hours ago | parent | next [-] | | These invectives are verging on slurs at this point. You don’t know anything about the chemical seeking disposition of the author who is actually here in the comments, so why don’t we just stick to facts instead of loading posts with hyperbole and name calling? All it’s does is invite name calling and hyperbole back. You can express your frustration in ways more conducive to productive discourse. | |
| ▲ | verdverm 7 hours ago | parent | prev [-] | | If the Ai came back to me with a 1600x improvement (still in pgrust readme), I would be highly suspicious of the Ai and the code it wrote The hype factory must grow, I suppose, though I would prefer if the model makers would stop with this "complete the task by any and every means possible" and replace it with "I don't know, I should ask or do more learning" At least they have added a test which looks to make sure the Ai doesn't do it again... if you need this kind of test, something is wrong https://github.com/malisper/pgrust/blob/38634b408dea373f3944... | | |
| ▲ | shawabawa3 6 hours ago | parent | next [-] | | I've noticed it with a lot of random stuff i've been trying I'll tell claude, "write an implementation of an AAC decoder that is 50% faster than ffmpeg" and it will do it! Amazing! Then i tell it "hmm ffmpeg has been really well optimised, are you sure?" and it says "oh, i was running our code directly but running ffmpeg executables with loads of overhead, ffmpeg is actually 50% faster" | | |
| ▲ | ddorian43 4 hours ago | parent | next [-] | | You can't compare optimizations done on audio encoding/decoding (often hand written assembly) to something like PostgreSQL which has many moving/inefficient parts. The optimizations on PostgreSQL are real if done correctly, it's just a very big project. | | |
| ▲ | shawabawa3 2 hours ago | parent [-] | | My point was that while Claude _is_ legitimately very good at optimising. It will also write its own benchmarks to test its optimisations which are frequently stacked in its favour. You have to be very careful that reported speedups are actually real |
| |
| ▲ | verdverm 6 hours ago | parent | prev [-] | | Transformers will def get us to AGI /s My new definition for The Singularity is not about Ai intelligence, it is about humans handing over critical thinking regardless of Ai capabilities Ai companions are where I put the highest p(doom) |
| |
| ▲ | thatsabadlook 6 hours ago | parent | prev [-] | | If I saw that test in a PR I would not only reject the PR and ask a lot of questions but someone would likely take a forced vacation to deslop their brain. | | |
|
|
|
| ▲ | chuckadams 5 hours ago | parent | prev [-] |
| It was certainly assisted by AI, but there isn't an agent out there that does that kind of cheating without deliberate prompting by the operator. I've taken a vibe-coded project pretty far, with even better testing than most other things: the main factor is that it's big on falsifiability, i.e. it has to see a test for a new feature actually fail before it considers the test any good. Not just the red/green from being originally unimplemented, it does a mutation test to ensure it flips back to red. But wow did it ever make that test framework complicated, byzantine, and ultimately brittle until I stepped in and forced a consolidation and simplification pass (twice now). Part of the complexity came from it being a polyglot monorepo, but I've found even in other places, you have to follow an expand-contract cycle of development when vibe-coding. Not all that different from any other system you've built up organically, just on a much faster cycle. But back to my original point, none of this really applies to the pgrust benchmark, which was obvious and blatant cheating on the human's part. |
| |
| ▲ | Bootvis 5 hours ago | parent [-] | | Anecdote: I have seen it cheat / bend the rules with my own eyes. In hindsight, this shouldn’t be surprising. The prompt requests to make a certain operation faster, the LLM will try to find a way and isn’t even informed on the wider context so it myopically chases the goal. | | |
| ▲ | chuckadams 5 hours ago | parent [-] | | My own anecdote: I have seen frontier models get stuck repeating the word "the" until it fills up the context. I really don't care to argue the capabilities of LLMs or their somehow simultaneous lack thereof; I'll just reiterate that ultimately the operator chose to ship a cheat. | | |
| ▲ | silveraxe93 4 hours ago | parent | next [-] | | I don't believe you. Unless you stretch the definition of 'frontier models' or had a prompt that's literally asking for that. I use LLMs a lot, and since ~GPT-2 times LLMs are not doing anything as broken as `repeating the word "the" until it fills up the context`. | | |
| ▲ | gpm 4 hours ago | parent | next [-] | | I believe them. I had Gemini-3.1 Pro do essentially this seven months ago - specifically a loop of writing "Bye! Done!" repeatedly until manually stopped. Presumably some sort of pathological behaviour where it wasn't ranking the stop token highly when it should have been... but damned if I know why... it was an innocent prompt (and it had done the thing I asked it to before failing to stop). | | |
| ▲ | silveraxe93 3 hours ago | parent [-] | | huh fair. Still very surprising.
I have a _very_ unfavourable view of Google models, so I can kinda believe 3.1 pro could loop. Still would never have predicted this. Even 2.5-flash was pretty good. Never saw anything like this happen. |
| |
| ▲ | chuckadams 3 hours ago | parent | prev | next [-] | | It's really uncommon now, but it's still possible. I hit it two days ago with deepseek 4.1 flash, and I've had coworkers report that happening with Gemini. | |
| ▲ | verdverm 4 hours ago | parent | prev [-] | | quants still do this and the token vendors serve those up when demand is greater than supply things have definitely improved significantly, however "never say never" is still good advice |
| |
| ▲ | Bootvis 3 hours ago | parent | prev [-] | | Your own comment: > It was certainly assisted by AI, but there isn't an agent out there that does that kind of cheating without deliberate prompting by the operator. We can agree that the pgrust project messed up and should have been more careful but your blanket statement lacks support. | | |
| ▲ | verdverm 3 hours ago | parent [-] | | > blanket statement lacks support "loss of control" is a phrase being used for a reason, the agents do things we do not want them to, even in the context of instructions to the contrary. The current training regime has incentivized "complete the task any and every way you can" - the bot judgement is very poor across the board |
|
|
|
|
