Tux@lemmy.world to Technology@lemmy.worldEnglish · 10 个月前Stack Overflow Website Trafficlemmy.worldimagemessage-square104fedilinkarrow-up1490arrow-down1119
arrow-up1371arrow-down1imageStack Overflow Website Trafficlemmy.worldTux@lemmy.world to Technology@lemmy.worldEnglish · 10 个月前message-square104fedilink
minus-squareflamingo_pinyata@sopuli.xyzlinkfedilinkEnglisharrow-up23arrow-down4·10 个月前Chat GPT is wonderful as a search engine for SO. It regurgitates the answers in a format easier to incorporate into your own project. The thing I’m worried about is a lack of new answers. You need data to train an LLM, what to do if nobody is producing it?
minus-squareGetOffMyLan@programming.devlinkfedilinkEnglisharrow-up4arrow-down2·10 个月前It already uses the docs and API references
minus-squareiii@mander.xyzlinkfedilinkEnglisharrow-up11arrow-down1·10 个月前I typically visit stack overflow when encountering edge cases and bugs not covered by the documentation.
minus-squareGetOffMyLan@programming.devlinkfedilinkEnglisharrow-up3arrow-down1·10 个月前If it has learned from the source code you’d be surprised how good it is at that as well. For docs it’s better, for other stuff it’s way worse than a human. It’s a shame so much stuff is locked up in discord these days.
minus-squareEager Eagle@lemmy.worldlinkfedilinkEnglisharrow-up3·10 个月前yeah, discord the the true black hole of information
minus-squareiii@mander.xyzlinkfedilinkEnglisharrow-up1arrow-down1·10 个月前Do you mean trained on the source code, or having the source code in context?
minus-squareGetOffMyLan@programming.devlinkfedilinkEnglisharrow-up1·10 个月前Trained on the source code. Yeah could also clone the repo and use copilot against it.
minus-squareMajorHavoc@programming.devlinkfedilinkEnglisharrow-up2·edit-210 个月前Ha! I have an AI for that! Gotcha! … On, but the AI trains now on other docs that I used an AI to write… … Oh shit…
Chat GPT is wonderful as a search engine for SO. It regurgitates the answers in a format easier to incorporate into your own project.
The thing I’m worried about is a lack of new answers. You need data to train an LLM, what to do if nobody is producing it?
It already uses the docs and API references
I typically visit stack overflow when encountering edge cases and bugs not covered by the documentation.
If it has learned from the source code you’d be surprised how good it is at that as well.
For docs it’s better, for other stuff it’s way worse than a human.
It’s a shame so much stuff is locked up in discord these days.
yeah, discord the the true black hole of information
Do you mean trained on the source code, or having the source code in context?
Trained on the source code.
Yeah could also clone the repo and use copilot against it.
But who writes the docs now
Ha! I have an AI for that! Gotcha!
…
On, but the AI trains now on other docs that I used an AI to write…
…
Oh shit…