darkport
Joined 8 years ago
Karma
54
Submissions
37
Member since
Feb 11
Recent submissions
Comment · 11 days ago
Comment · 1 month ago
FYI you can spin up 4xH200s at ~$9/hr on spot. Just ask Codex and it'll do it end to end.
Comment · 8 months ago
Thanks for the suggestion, will look into it.
Comment · 8 months ago
We’re pretty new! :) They didn’t want to provide comment on our post but they did offer comment via The Register.
Comment · 8 months ago
Founder of CodeWall here. It's quite funny because whilst an LLM did write the bulk of the posts factual content (based on the agents findings), I wrote the intro and summary at the end. That's just my writing style. Feel free to read my personal blog to compare: https://darkport.co.uk
Comment · 1 year ago
I think this is true for deeply complex problems, but For everyday tasks an LLM is infinitely “better”.
And by better, I don’t mean in terms of code quality because ultimately that doesn’t matter for shipping code/products, as long as it works.
What does matter is speed. And an LLM speeds me up at least 10x.
Comment · 5 years ago
I've always wanted to do something similar at scale. Generate all possible random mobile numbers 11^10, check if they have a WhatsApp profile pic and run it through AWS' rekognition celebrity model (https://docs.aws.amazon.com/rekognition/latest/dg/celebritie...). You could identify the personal numbers for a _lot_ of VIPs, politicians, etc.
Comment · 5 years ago
I created a tool awhile back that pretty much does this https://github.com/eth0izzle/Needl - it’s gone stale so looking for new contributors
Comment · 5 years ago
What year is it?
Comment · 5 years ago
Eh, BlockCypher are based in CA. Court order could force them to sinkhole any API requests to that wallet.
And to make it interesting, I setup a live stream showing every single attack attempt happening live https://www.youtube.com/watch?v=w7_EJWqRzvw
Have fun!