Just stumbled upon this blog which details out testing and validating large GPU clusters before running training workloads. Any other similar blogs which adds more nuance in terms of debugging the issues once we identify them as well?
I just built a simple chrome extension which uses Groq with a whisper model to do Speech to Text so that we can give speech inputs to Claude. I really liked being able to do speech to text with ChatGPT and missed that quite a bit with Claude, hence built this.
Why Groq?
They have a free tier and super fast, so anyone can create an account and add their API key to the extension.
Privacy?
The only API calls that are there are to Groq servers, so as long as you have read their T&C you should be fine
This was done and tested in a few hours and quite buggy still but works. Feel free to drop some feedback. Will push more updates, if anyone else actually finds this useful
Just started working on this small project where one can just convert their whatsapp conversations into an instruction dataset which can be finetuned with any OSS models for creating a clone of themselves.
Have added sensitive info redaction and also general whatsapp messages redaction when parsing and compiling the dataset.
Very early but appreciate any suggestions or discussions around this.
I was just dumping all of my thoughts with respect to LLMs on how to setup and manage a RAG system. Thought it will be useful for people to think through as well, hence sharing here.
Export Chat is a ChatGPT plugin which lets you export your ChatGPT conversations as a PDF/Doc with just a single message. Just type "export the previous message" or conversation.
Find it under the list of plugins in ChatGPT.
Checkout exporter.hexonlabs.com for understanding how to create better exports. Do let me know any feedback!
Hey Hacker News folks! I'm an indie developer, and I've just built a nifty little plugin to help keep your personal data safe while using ChatGPT. With ChatGPT becoming increasingly popular, it's easy to accidentally share sensitive info like phone numbers or email addresses. My plugin displays a warning when it detects you're about to enter personal details into the message window.
This can be a lifesaver in professional environments, too. IT managers can enforce it on office machines to ensure employees don't unintentionally leak confidential data through ChatGPT. I'm excited to share this with you all and hope it'll make your ChatGPT experience more secure and privacy-conscious. Give it a try and let me know your thoughts!
Tried building a chrome plugin completely by GPT-4 generated code for fun and got it published a few days back.
The name and description was also generated by ChatGPT, just asked it to be more SEO friendly. Consider this a mini experiment and nothing technical or fancy.
