If I'm looking for something recent or that I already know the approximate date the note was made on, I just read through the notes from the relevant time period. I also keep notes in my physical notebooks about what information is found in which note textfile on the computer.
In practice, I rarely actually need to grep or otherwise use tools to search through the notes. My eyes work fine (and, for me, are even better because I get reminded of the context in which the notes were taken).
The odd thing about the paper notebooks is that I rarely actually need to use them. Just the act of making the notes greatly enhances my natural recall of them anyway. If the notes are something deeply technical (a bunch of raw data, schematics, whatever), having written them by hand also makes me remember where I wrote them. That sort of thing only happens when handwriting, though (which is why I came back to handwriting notes). It doesn't happen at all if I've typed them into a computer.
I've probably tried just about every "knowledge manager" or note-taking application there is at one time or another, but for me and how my brain works, nothing comes close to being as effective as writing things in notebooks.
Well, it started off this way, but I went through several iterations with the audit prompt and the system prompt to improve the issue detection, the solutions suggested, tag them, reduce hallucinations, provide approximate image coordinates, provide examples to the model, etc.
It's currently at over 20 lines of prompting and I guess this will grow over time.
Glad to hear it did find something that you can correct.
Regarding the points about fine print (and the screenshot not loaded correctly) - would you kindly reply with the URL of the website you audited here, or email it to me to feedback at flawless.is ?
I'd love to take a look and see if these issues could be fixed or improved.
I think GPT-4V perception of size might be distorted, since it downsizes everything to be 512px wide before scanning it. I wonder how can this be overcome, I'll try to play with the prompts to instruct it specifically about sizes.
Regarding the "Meet Slack for Enterprise" - you're right, it is weird, looks like it's hallucinating. I'll try and dig deeper.
I’m still confused though, let’s say I “fix” all the problems it gave me, and afterwards if I want to run it again with those fixes, I will need to pay again?
I think now I better understand your original question.
Yeah, to run an audit again on that same site, you'd need to pay again.
Otherwise, I'll have to put in place user management & user rate limits to avoid abuse, since someone could run this 50 times on their website within a given day, and currently OpenAI limits us to 100 queries per day.
I understand clearly now, thank you very much for your detailed responses and an inspiring tool you shared with us!
As a solo full-stack web dev from Turkey, I will be closely following this tool's future, and looking forward to your continued development of it.
For an audience like me (solo developers) this is potentially incredibly useful, and at worst a nice heuristic apparatus that’s worth paying, so thank you again for making my job easier and aiding me deliver more quality product!
Eventually, Hacker News ended up bringing 20,000+ visitors.
Had to upgrade our urlbox screenshot API account twice in 1 hour just to keep up with the demand.
This Hacker News post could have cost $1,000+ if the API rate limit hadn't kicked in. Oh well, silver linings...
Since almost no one could use the app (too many people, and not enough quota from OpenAI), I added a $1.99 one-time payment per audit. This would probably decrease the number of users and also help cover the insanely high costs.
Say you're looking for something from a few days ago, you grep all recent text files to find the relevant note?
How does it work with a physical notebook, though? I guess that's harder to grep