News for hackers. Stuff that matters.

kanxx030

Re:I Built a Crowdsourced Site to Track Public WiFi Speeds on Thursday February 06, 2025 @06:47PM (#42967675)
As a remote worker, I always find it frustrating that there wasn't a site that lists public WiFi speeds — so I built one.
Re: on Wednesday July 24, 2024 @08:01PM (#41063499)
We’re on a mission to transform the legal industry with GenAI technology, and we need your insights! Whether you’re a lawyer, developer, or just interested in legal tech, your input can make a huge difference. Take our short survey and help us build a smarter legal future.
interesting read. I was looking into this a while ago- company had a monorepo vs. polyrepo debate.

Plexiglass: A toolbox for testing against adversarial attacks in DNNs and LLMs

Hi everyone, my name is Enoch and I am a researcher studying deep generative models.I've started this project called Plexiglass a while back, which started off as a torch toolbox for adversarial research in DCNNs. I am now rebooting it as a toolbox for testing against adversarial attacks in both DNNs and LLMs.Idea is to test your DCNNs against adversarial attacks such as fast gradient sign...

( Read More... | 2 comments | 3 points | on HN )
Re: on Wednesday December 06, 2023 @06:36PM (#38550978)
Hi everyone, my name is Enoch and I am a researcher studying deep generative models.

I've started this project called Plexiglass a while back, which started off as a torch toolbox for adversarial research in DCNNs. I am now rebooting it as a toolbox for testing against adversarial attacks in both DNNs and LLMs.

Idea is to test your DCNNs against adversarial attacks such as fast gradient sign method and toxic prompts in LLMs.

I would very much appreciate contributions, I need more devs as I'm too busy to do this all by myself .

Repo is here: https://github.com/kortex-labs/plexiglass

Re: on Thursday November 16, 2023 @06:34PM (#38297190)
We are trying to build the largest prompt template db to date- all free and open-sourced!
Re: on Tuesday October 24, 2023 @03:37PM (#38004266)
Hi all, my wife and I have recently started a new publication called The ML Practioner.

If you're interested in writing for us, please send us a link of your unpublished draft to our LinkedIn page (https://www.linkedin.com/company/the-ml-practitioner).

Either way, please subscribe to us if you're interested in this kind of content!

Re: on Thursday August 17, 2023 @05:39AM (#37159300)
same as title :) please star and contribute!
Re: on Wednesday August 16, 2023 @09:52AM (#37147002)
I'm looking for some early engineers to help build this amazing framework for LLM testing. Please help!
Re: on Tuesday August 15, 2023 @12:18PM (#37135807)
Hi all, I’m looking for early contributors to our LLM testing framework. Please star and contribute :)
Re:Our latest project: fact-checking for LLMs on Saturday August 12, 2023 @08:06PM (#37105321)
We are creating an open-source framework for LLM fact-checking here!
Re:Set Up My First NFT Store on OpenSea on Friday April 30, 2021 @08:12PM (#27001377)
I was never a huge believer in crypto but with all the free time I had during lockdown I started do my own research on blockchain- now I'm a firm believer. As a seasoned urban photographer, I've recently decided to set up my own store on OpenSea. It would mean a lot if you can check out my listings here, or even simply sharing them would help me tremendously.
Re:Kalman Filter in Python on Wednesday March 17, 2021 @09:10PM (#26498763)
I know this may be very basic for a lot of you ML experts, but I just spent an hour learning and implementing a simple Kalman filter here: https://github.com/enochkan/kalmanpy and it worked :D pretty darn proud of myself

Please check it out and would appreciate any feedbacks.. my implementation is far from perfect and I plan on implementing more as my knowledge grows.

Re:Torch Metrics Library on Saturday March 13, 2021 @07:54PM (#26451707)
A new library I'm working on. Please feel free to use it/ contribute :]
Re:Torch-metrics: a model evaluation package for PyTorch on Monday November 16, 2020 @02:42AM (#25109150)
Pytorch does not have a built-in libary torch.metrics for model evaluation metrics. This python library serves as a custom library to provide common evaluation metrics in Pytorch, similar to tf.keras.metrics. This is similar to the metrics library in PyTorch Lightning.
Plexiglass is a PyTorch toolbox for cybersecurity research and testing against adversarial attacks and deepfakes. Contributions/ feature requests are welcome!