| ▲ | throw839948499 2 hours ago |
| If the solution is so simple, why claude did not found it? At this point we can assume, it is better than 90% of engineers (including me). After three decades of outsourcing to lowest bidder, I do not buy that humans are somehow better! > patient, old school troubleshooting I usually see similar arguments around systems with major red flags (no docs, poor CI, decade ago no CVS...). And engineers with private stash of workarounds for job security! Claude does not do anything special. Or perhaps claude was misconfigured, it had no access to relevant part of system, and it tryied to work within its limitation. Often it means decompiling binaries in desperate loop... |
|
| ▲ | shakna 2 hours ago | parent | next [-] |
| Claude regular spits out six helper functions instead of... A twenty line for loop. It overengineers most things. Overabstracting, deduplicating things that don't need to be. Building metaclasses because it saw a single orchestrator in the whole codebase. If it is a better engineer than you... You need practice. |
| |
| ▲ | adjejmxbdjdn an hour ago | parent | next [-] | | The funny thing is that if you never understand the codebase then you will keep thinking Claude is doing a great work delivering all this incredible software, when all it has done is created unnecessary tech debt. | |
| ▲ | jjav an hour ago | parent | prev | next [-] | | > A twenty line for loop. It overengineers most things. Anecdote I like to tell.. I was working on a financial planning software, intentionally purely vibe coded as an experiment. I eventually discovered AI had implemented seven duplicate copies of tax calculation functions. All of them different. All of them wrong. All of them giving different answers for same input. Not even the most junior of newbie junior engineers would do something this crazy. But AI was happy to do it. It will solve the immediate problem, efficiently. Even if the most efficient solution is something ridiculous like this. | | |
| ▲ | ilija139 19 minutes ago | parent | next [-] | | I have also a weird story to tell that a human did and it is as crazy as this. It happen in 2019 so no LLMs at all. A person that was hired as an expert in our startup spent more than one week full time working on implementing his solution to the problem we were having. I checked the code after one week to see the progress and was curious how they are implementing an already crazy sounding idea.
I found that the whole week was spent re-implementing in python, python's built-in "float" function. That was it, the whole code was just that. Our problem was related to financial services and their implementation of "float" was not even correct. | |
| ▲ | gnz11 14 minutes ago | parent | prev | next [-] | | Which model though? I have similar anecdotes but all with older models. The jump in capabilities in the last 6 months has been substantial. | | | |
| ▲ | UpsideDownRide 21 minutes ago | parent | prev [-] | | For some definitions of efficiency. |
| |
| ▲ | Foobar8568 an hour ago | parent | prev | next [-] | | Oh and how is it any different than most software engineers? How many times I heard ORM are bad only to recreate the same shit? How many times I heard ORM had bad performance and see 1+n stuff everywhere? How many times I have seen tight coupling in the name of DRY? | | |
| ▲ | shakna 18 minutes ago | parent [-] | | Its different, in that when you teach that engineer, they either leave because now they hate you, or they grow. They change to meet the standards of a project, rather than inventing their own. We don't get seniors, without juniors. I'd say more than half the job, is just... Learning. People grow. |
| |
| ▲ | throw839948499 an hour ago | parent | prev | next [-] | | I am former java enterprise dev, so yes I often code this way. Unit testing, decomposition... Some projects CI refuse to merge commits with 20 line loop and duplicated code... But that is not a point. Claude can code tight compact loops, it just needs to be instructed to do so! If it does "enterprise code", it means it had no instructions about code style. If your documentation, spec, agent.md does not have proper guidance on coding style... yet another red flag! | | |
| ▲ | shakna 20 minutes ago | parent [-] | | > it just needs to be instructed to do so! Considering how often it overrules, its own rules? |
| |
| ▲ | raverbashing 39 minutes ago | parent | prev [-] | | 100% It is my pet peeve with Claude and why I don't prefer it for most stuff (also the comment spam - but that's a all of them in a way or another) |
|
|
| ▲ | Sharlin 2 hours ago | parent | prev | next [-] |
| So after 30 years of outsourcing to the bottom 10%, you think Claude is better than the bottom 90% even though it’s so stupid that it doesn’t even know it should ask for advice or more information when it’s stuck? |
| |
| ▲ | throw839948499 an hour ago | parent [-] | | It just follows instructions you give it. Some asian devs will go for weeks without asking for help, all while giving amazing fake status reports. Loosing face etc... | | |
| ▲ | Sharlin an hour ago | parent | next [-] | | Do you think those devs are in the top 10% of all devs like you said Claude is? Or is the bar suddenly much lower after all? | |
| ▲ | tannertech an hour ago | parent | prev [-] | | You're comparing scammers to incompetence |
|
|
|
| ▲ | alex_smart an hour ago | parent | prev | next [-] |
| Because simplicity is hard and often the result of careful thought. Anybody can keep piling pile of shit on top of pile of shit which is why that sort of code is so common in our industry. |
|
| ▲ | SyneRyder an hour ago | parent | prev | next [-] |
| While I actually agree with you (though, outsourcing to lowest bidder would account for much of what you're seeing with humans), I just saw Bug Hunt Bench scores that gave me some pause: https://x.com/PawelHuryn/status/2095982259761475945 https://bughunt.productcompass.pm/?preset=all Claude Opus 4.8 ranks near last on this Bug Hunt benchmark, and missed 96% of the deliberately introduced bugs. If you're a developer who has been falling back to Opus 4.8 because of how Opus 5 talks, and Fable 5 being so expensive that it needs to be rationed... well, turns out Opus 4.8 can actually be quite poor for finding bugs. (Which feels weird to me, because Opus 4.6 fixed a bug that myself and a group of humans had been hunting down for over a decade. Models are spiky.) Also surprising to me: Luna Max performing better than Fable 5.1 High, at least on this benchmark. But Astra 6 & Fable 5.1 on Max both perform at the top as you would expect. |
| |
| ▲ | throw839948499 an hour ago | parent [-] | | Still, basic debuging and trouble shooting is where LLM generally shine. Any model can bisect git history and isolate newly introduced bug. If model can not automatically reproduce bug, while human manually can... you got a problem in CI. > Luna Max performing better than Fable 5.1 High Perhaps you are reading too many benchmarks. Edit for answer : I agree Luna is great cheap model. But if Fable was hitting security limits, yet was still included in benchmarks... What flies better? Elephant or paper plane. You can make objective benchmark about that. But not much value for logistics company | | |
| ▲ | SyneRyder 23 minutes ago | parent [-] | | > Perhaps you are reading too many benchmarks. Maybe, but at least the benchmark provides an objective measurement of the codebase it is tested on. You're also assuming the bugs are newly introduced / regressions. I can give a concrete example - Fable will not interact with bugs that result in writing to null pointers in C code. That triggers the guardrails and ends the session. If Luna (or GLM Flash, etc) will fix those kinds of memory bugs, that immediately puts it ahead of Fable in some ways, no matter how tiny Luna is. Again, models are spiky. I still agree with your initial point! It's LLMs all the way down over here. It would need to be a particularly gnarly bug & an exceptionally talented human for me to want to pay another human to work on fixing it now. |
|
|
|
| ▲ | gspr 2 hours ago | parent | prev | next [-] |
| > At this point we can assume, it is better than 90% of engineers (including me). Hard disagree. We absolutely cannot assume that. You can posit it, and we can have an informed debate about it. This is what irks me the most about LLM fans: they constantly try to reframe the debate to have their worldview as the agreed-upon starting point. |
|
| ▲ | bob1029 2 hours ago | parent | prev [-] |
| That final 10% is the hard part. 90% is easy. |
