saharhash··on Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromisedEasy tool to check if you/other repos were expoed https://litellm-compromised.com
saharhash··on Show HN: Documind – Open-source AI tool to turn documents into structured dataVision Language Model like Qwen VL https://github.com/QwenLM/Qwen2-VL or CoPali https://huggingface.co/blog/manu/colpali
saharhash··on [dead]A set of experiments with the new GPT-4V demonstrating its potential in making a whole industry obsolete.
saharhash··on Ask HN: Which are the best newsletters to keep informed on AI development?http://aitidbits.ai for a roundup of the recent AI papers, tools, and open-source libraries
saharhash··on This Image Does Not ExistAdded a few dozens of images earlier today and add more tomorrow. Let me know how it goes.
saharhash··on This Image Does Not ExistHi all, the author of ThisImageDoesnotExist here - thanks for all the great feedback! I've just added a few dozens of human-generated images and improved the randomization logic.Looking forward to getting further feedback.
saharhash··on Show HN: Open-source real-time transcription playground (React, Python, GCP)That's a great idea as for the next engine to add. The plan is to have multiple ones and not only Google's Speech API.
saharhash··on Show HN: Open-source real-time transcription playground (React, Python, GCP)The plugin url doesn't seem to work anymore
saharhash··on Show HN: Open-source real-time transcription playground (React, Python, GCP)Agreed, though what I was mainly missing with DeepSpeech was Speaker Diarization, which Google Speech API supports.