| ▲ | audunw 2 hours ago |
| Would recommend checking out the Zig state of the (tagged) union as well. https://youtu.be/zwi5b5xSsKA?is=PTjJJjSnVMdRuZag It may surprise some people here to see that Andrew is warming up to using LLMs to discover bugs (inspired by results from SQLlite) and considers it a tool on the path to getting to bug free software. |
|
| ▲ | saghm an hour ago | parent | next [-] |
| > It may surprise some people here to see that Andrew is warming up to using LLMs to discover bugs (inspired by results from SQLlite) and considers it a tool on the path to getting to bug free software. Someone in the thread below says their bug was closed because of mentioning that they use AI to confirm the bug they had encountered. Is he going to go back and reopen all of those now that he learned what pretty much everyone else already knew? |
| |
| ▲ | idle_zealot an hour ago | parent | next [-] | | > Someone in the thread below says their bug was closed because of mentioning that they use AI to confirm the bug they had encountered I don't know about this particular case, but if I saw someone report a bug and as evidence claim they had X Y and Z LLMs verify it I would be pretty upset. If you're going to use an LLM to make a replication, just do that and give me the replication, don't point to your notoriously error-prone tools as though they lend your report credence. It's in a similar vein to people who reply to questions with "well Claude says: <chat transcript dump>" | | |
| ▲ | manwe150 2 minutes ago | parent | next [-] | | I feel very torn as a maintainer on this, since the only way to respond to the increased noise from AI has been to have AI do the research for me to extract all the links and line numbers I used to have to find by hand to explain why the PR needs more effort to be completed. But I also will be highly dismissive of any submitter who just posts AI text without cleaning it up first. It feels hypocritical, but the alternative is that I just can’t respond to most people instead due to limited bandwidth. I mark if something comes directly from the LLM though and to try to express my degree of confidence in its claims. | |
| ▲ | xdavidliu 23 minutes ago | parent | prev [-] | | > It's in a similar vein to people who reply to questions with "well Claude says: <chat transcript dump>" or substantially worse: "<chat transcript dump>" |
| |
| ▲ | itishappy 40 minutes ago | parent | prev | next [-] | | Why? Shouldn't everybody already know that using AI to find bugs for oneself is amazingly efficient, but using AI to submit bug reports for others is quite the opposite. Burden of verification and all. | |
| ▲ | mjburgess an hour ago | parent | prev | next [-] | | There's a difference between Opus 4.5 and Astra 6 | | |
| ▲ | f33d5173 an hour ago | parent [-] | | With regards to whether when it finds a legitimate bug, it should be given weight? | | |
| |
| ▲ | vitaminCPP 44 minutes ago | parent | prev | next [-] | | citation needed | |
| ▲ | nelox 28 minutes ago | parent | prev [-] | | [flagged] |
|
|
| ▲ | mwkaufma 29 minutes ago | parent | prev | next [-] |
| Warming up to LLMS... explicitly _after_ full branch-coverage and fuzzing. |
|
| ▲ | fukaiall 23 minutes ago | parent | prev | next [-] |
| I personally think using AI is of no problem for certain cases. It is absolutely pissing off when someone tries to generate slops that too verbose to review only to increase the complexity of the codebase meaninglessly. |
|
| ▲ | kasajian an hour ago | parent | prev [-] |
| [flagged] |
| |
| ▲ | tinfoilhatter an hour ago | parent [-] | | It boggles the mind that people believe anyone that thinks differently from them is automatically utterly stupid. Actually, on second thought, it really doesn't. Indoctrination and herd mentality are quite the things. |
|
