Tux@lemmy.world to Technology@lemmy.worldEnglish · 8 days agoStack Overflow Website Trafficlemmy.worldimagemessage-square105fedilinkarrow-up1491arrow-down1120
arrow-up1371arrow-down1imageStack Overflow Website Trafficlemmy.worldTux@lemmy.world to Technology@lemmy.worldEnglish · 8 days agomessage-square105fedilink
minus-squareflamingo_pinyata@sopuli.xyzlinkfedilinkEnglisharrow-up23arrow-down4·8 days agoChat 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-down2·8 days agoIt already uses the docs and API references
minus-squareMajorHavoc@programming.devlinkfedilinkEnglisharrow-up2·edit-27 days agoHa! 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…
minus-squareiii@mander.xyzlinkfedilinkEnglisharrow-up11arrow-down1·8 days agoI typically visit stack overflow when encountering edge cases and bugs not covered by the documentation.
minus-squareGetOffMyLan@programming.devlinkfedilinkEnglisharrow-up3arrow-down1·8 days agoIf 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-up3·7 days agoyeah, discord the the true black hole of information
minus-squareiii@mander.xyzlinkfedilinkEnglisharrow-up1arrow-down1·8 days agoDo you mean trained on the source code, or having the source code in context?
minus-squareGetOffMyLan@programming.devlinkfedilinkEnglisharrow-up1·8 days agoTrained on the source code. Yeah could also clone the repo and use copilot against it.
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
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…
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.