Drew@sopuli.xyzM to Programming Circlejerk@programming.dev · 2 months agoStarting every coding task with a promptsopuli.xyzimagemessage-square32linkfedilinkarrow-up1121arrow-down11file-text
arrow-up1120arrow-down1imageStarting every coding task with a promptsopuli.xyzDrew@sopuli.xyzM to Programming Circlejerk@programming.dev · 2 months agomessage-square32linkfedilinkfile-text
source: https://www.linkedin.com/posts/zachlloyd_anyone-else-having-a-hard-time-getting-their-activity-7333511252666662913-RK7g
minus-squaresturger@sh.itjust.workslinkfedilinkEnglisharrow-up11·2 months agoI still don’t understand why we’re using humans to review AI code. Shouldn’t AIs be reviewing the code? We’re letting AIs do the fun part (coding) and forcing humans to review (the worst part) reams more janky code.
minus-squaregreenskye@lemm.eelinkfedilinkEnglisharrow-up8·2 months agoAI’s get the fun part of everything right now. AI gets writing, humans get editing. AIs get drawing, humans get fixing hands and details, etc etc
minus-squareFizzyOrange@programming.devlinkfedilinkarrow-up4·2 months agoAI’s aren’t smart enough yet. But plenty of people are also using them to review code.
minus-squareBeacon@fedia.iolinkfedilinkarrow-up2arrow-down1·2 months agoWhat are the results if you take code written by one brand of ai and then have another brand of ai review it? Like use chatgpt to write code, and then ask copilot if the generated code has any errors and will work as intended?
minus-squareNoForwardslashS@sopuli.xyzlinkfedilinkarrow-up5·2 months agoI don’t know, if I put my hand in a fan and then put that mutilated hand into another brand of fan, do you think that might fix it?
minus-squareFizzyOrange@programming.devlinkfedilinkarrow-up2·2 months agoInteresting idea, I’ve never tried that. I feel like it wouldn’t be a silver bullet but you might get slightly better results I guess.
I still don’t understand why we’re using humans to review AI code. Shouldn’t AIs be reviewing the code?
We’re letting AIs do the fun part (coding) and forcing humans to review (the worst part) reams more janky code.
AI’s get the fun part of everything right now. AI gets writing, humans get editing. AIs get drawing, humans get fixing hands and details, etc etc
AI’s aren’t smart enough yet. But plenty of people are also using them to review code.
What are the results if you take code written by one brand of ai and then have another brand of ai review it? Like use chatgpt to write code, and then ask copilot if the generated code has any errors and will work as intended?
I don’t know, if I put my hand in a fan and then put that mutilated hand into another brand of fan, do you think that might fix it?
Interesting idea, I’ve never tried that. I feel like it wouldn’t be a silver bullet but you might get slightly better results I guess.