| |
| ▲ | dhorthy 2 days ago | parent [-] | | I read it. i agree this is out of touch. Not because the things its saying are wrong, but because the things its saying have been true for almost a year now. They are not "getting worse" they "have been bad". I am staggered to find this article qualifies as "news". If you're going to write about something that's been true and discussed widely online for a year+, at least have the awareness/integrity to not brand it as "this new thing is happening". | | |
| ▲ | flumpcakes 2 days ago | parent | next [-] | | Perhaps the advertising money from the big AI money sinks is running out and we are finally seeing more AI scepticism articles. | |
| ▲ | minimaxir 2 days ago | parent | prev | next [-] | | > They are not "getting worse" they "have been bad". The agents available in January 2025 were much much worse than the agents available in November 2025. | | |
| ▲ | Snuggly73 2 days ago | parent [-] | | Yes, and for some cases no. The models are gotten very good, but I rather have an obviously broken pile of crap that I can spot immediately, than something that is deep fried with RL to always succeed, but has subtle problems that someone will lgtm :( I guess its not much different with human written code, but the models seem to have weirdly inhuman failures - like, you would just skim some code, cause you just cant believe that anyone can do it wrong, and it turns out to be. | | |
| ▲ | minimaxir 2 days ago | parent [-] | | That's what test cases are for, which is good for both humans and nonhumans. | | |
| ▲ | Snuggly73 2 days ago | parent [-] | | Test cases are great, but not a total solution. Can you write a test case for the add_numbers(a, b) function? | | |
| ▲ | Snuggly73 2 days ago | parent | next [-] | | Well, for some reason it doesnt let me respond to the child comments :( The problem (which should be obvious) is that with a/b real you cant construct an exhaustive input/output set. The test case can just prove the presence of a bug, but not its absence. Another category of problems that you cant just test and have to prove is concurrency problems. And so forth and so on. | |
| ▲ | minimaxir 2 days ago | parent | prev [-] | | Of course you can. You can write test cases for anything. Even an add_numbers function can have bugs, e.g. you have to ensure the inputs are numbers. Most coding agents would catch this in loosely-typed languages. |
|
|
|
| |
| ▲ | Snuggly73 2 days ago | parent | prev [-] | | I mean "have been bad" doesnt exclude "getting worse" right :) |
|
|
