21–30 of 32 posts
> Open chatgpt in second tab > Type what chatgpt says yourself The only "AI proof" writing tool is those blue books you take exams on in college.
No need for a second tab (focus switch is trackable) when you have a phone.
I pulled up a 2nd browser next to your site. I typed the prompt into Gemini, and manually typed what Gemini said and removed em dashes as I typed. It said it was 100% genuine.
Maybe I need to punish tab/windows switches more severely? Or perhaps require webcam and do eye tracking?
What, so I can't look up into my memories like I do in a natural conversation?
How would you account for accessibility issues where test takers can't control they're eyes?
Earlier quoted context omitted.
Maybe I need to punish tab/windows switches more severely? Or perhaps require webcam and do eye tracking?
I only switched tab/windows once (to input the question). So I'm not sure how severely you'd want to rate that. The webcam doing eye tracking might help if the person isn't good a typing and can copy one side without checking if the other is okay...
I used this: #!/usr/bin/python3 import subprocess import time import random with open("/tmp/x") as f: t = f.read() for c in t: subprocess.call([ "xdotool", "type", c ]) time.sleep(abs(random.gauss(0,0.07))) And pasted a random Hacker News comment: Authenticity Score 81 Highly Authentic Words per minute: 162 Keystroke variance: 52ms Paste attempts: 0 Window/tab switches: 4 Pauses (≥10s): 0 DOM manipulations: 0 You fai…
That's cool, thanks for sharing. Is there a way to detect this approach?
Put it this way, let's say someone recorded typing in the paragraph that you presented but saved the keystrokes, pauses, etc. Now they replay it back, with all the pauses and keystrokes, maybe with the `xdotool` as above, how could you possibly know the difference?
Your method is playing a statistical game of key presses, pauses, etc. Anyone who understands your method will probably not only be able to create a distribution that matches what you expect but could, in theory, create something that looks completely inhuman but will sneak past your statistical tests.
I used this: #!/usr/bin/python3 import subprocess import time import random with open("/tmp/x") as f: t = f.read() for c in t: subprocess.call([ "xdotool", "type", c ]) time.sleep(abs(random.gauss(0,0.07))) And pasted a random Hacker News comment: Authenticity Score 81 Highly Authentic Words per minute: 162 Keystroke variance: 52ms Paste attempts: 0 Window/tab switches: 4 Pauses (≥10s): 0 DOM manipulations: 0 You fai…
Do you have any other command line tool recommendations?
I clicked begin and immediately alt tabbed to ChatGPT. I took a screenshot of the prompt and pasted to ChatGPT, with the instruction "Write a 1 paragraph response as if you were a human". I alt tabbed back to the writing website and started typing ChatGPTs response. I intentionally added a few pauses in places where I thought I might pause, and deleted words a couple times. I also slightly changed the last sentence f…
The “self”-(un)awareness is almost endearing (though some might be your higher level instructions). It summarizes—correctly IME— that it’s basically an ~inept~ typical middle/upper manager/“visionary”, replete with a CorpSpeak promise to circle back and “fill in the gaps”… which it does with the consistency and accuracy of a samesaid cat-turd-ingester.
Does make me wish that the folks nodding along in meatspace would/could be similarly “honest” about this same phenomenon.