bing_dai
Re:In many cases we need something less like AI and more like a basic ...
on Sunday July 14, 2024 @01:04PM (#40962011)
Could you provide an example?
Show HN: An Open Source "News Feed" for AI-Focused Videos on YouTube
Source Code: https://github.com/bingdai/summaryfeedsSummary Feeds (https://www.summaryfeeds.com) is a website that:- Fetches transcripts of AI-focused YouTube videos, using the YouTube Transcript API by pypi.org.- Uses OpenAI's GPT-3.5-turbo-16k to summarize video transcripts.- Presents summaries in an easily readable format.- Organized interface to browse video summaries by date.Tech Stack:-...
Re:Ask HN: What have you built with LLMs?
on Monday February 05, 2024 @05:13PM (#39267983)
Project 1
— Source code: https://github.com/bingdai/summaryfeeds. The code is for Summary Feeds (https://www.summaryfeeds.com). It shows summaries of AI-related YouTube Channels.
****
Project 2 - I also built a YouTube summarizer for individual video called Summary Cat (https://www.summarycat.com). It is not open source for now. The stack is very similar to project 1.
****
And yes I like summarizing YouTube videos:)
Are LLMs going to drive a swing back to on prem?
Evaluating the Expense of OpenAI Whisper: API or Self-Hosted?
Re:Ask HN: Comment here about whatever you're passionate about at the ...
on Monday November 06, 2023 @06:56PM (#38171088)
Mainly because knowledge about Christianity is the most physically accessible to me, as I am a next-door neighbour to a Theology professor of New Testament.
Re:Ask HN: Comment here about whatever you're passionate about at the ...
on Monday November 06, 2023 @06:46PM (#38170970)
Learning about Christianity, after being an atheist my whole life thus far.
Ask HN: Are You Religious?
A “Yes/No/Maybe” would do.If you’d like to: share what religion it is!For me: Maybe Christian.
Re:Ask HN: Show me your half baked project
on Thursday October 12, 2023 @07:14PM (#37864398)
https://www.summarycat.com/
I made a YouTube summarizer, Summary Cat.
————————-
Technical Details
Goal: Generate brief and coherent summaries from YouTube video transcripts
Motivation of building this project: to save myself time watching videos that are too long.
Stack • Frontend: HTML/CSS, plus a tiny bit of Javascript for handling the button • Backend: Python/Flask • Flask served as the backend web framework, handling routes and integrating various services. • Front+Backend has about 500 lines in total • Hosting: AWS Free-tier Elastic Beanstalk • Database: AWS Free-tier RDS
APIs: • For grabbing YouTube's transcripts: I used youtube-transcript-api (https://pypi.org/project/youtube-transcript-api/) • For summarizing the transcripts: I used OpenAI's GPT-3.5-turbo-16k: https://platform.openai.com/docs/guides/gpt. • I used GPT-3.5 because GPT-4 is quite a lot more expensive (roughly 10X).
My Prompt (Super Simple!) • "please summarize the following text into a few paragraphs:" + the full transcript.
Thoughts about GPT-4 vs GPT-3.5-Turbo-16k or Summary Cat • GPT-4 was 20% better for "summary quality" • GPT-4 feels 50% faster • However, GPT-4 is about 10X as expensive as GPT-3.5
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @06:59PM (#37618892)
Ah ha! Great point!
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @06:34PM (#37618667)
Hi, I used this Python library (https://pypi.org/project/youtube-transcript-api/) to get transcripts. It works great.
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @06:20PM (#37618502)
I agree that this is happening " an arms race between youtube forcing creators to make videos 8 mins long min to be able to get mid roll ads and people coming up with ways to summarize the transcript." Along the same line: I have been thinking about how my Summary Cat might mean for the content creators. How would it impact their income?
Your "use the summarizer to re-cut the videos" is fantastic!
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @06:12PM (#37618444)
Sorry, could you please explain what you mean? I am not really quite getting it. What might happen if a Prompt Engineer get a hold of it?
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @06:00PM (#37618355)
I think your suspicion might be correct: long videos exceeds GPT token limitation (16,385 tokens in my case of GPT-3.5-turbo-16k).
Thanks for your suggestion about how to address it.
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @05:45PM (#37618205)
If you don't mind, could you share an example of such long video? I'd love to debug it.
As for non-Youtube URL: I indeed do not handle that error right now :D. Thanks so much for bringing it up!
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @05:43PM (#37618195)
You are right. The site doesn't handle non-English videos, but that is on the roadmap. Thanks so much!
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @05:35PM (#37618094)
More than happy to share!
----------- My prompt is super simple. It is "please summarize the following text into a few paragraphs:" + the full transcript. -----------
Seriously that's it!
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @05:30PM (#37618043)
Hello, GPT-4 is not worth it in my experience so far!
I would say, GPT-4 is - 20% better at "summary quality" - feels 50% faster - BUT, 10X as expensive.
So using GPT-3.5 was the right choice for me at this point.
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @04:55PM (#37617649)
Thanks for the question... Any sample videos you are thinking of?
Summary Cat doesn't work for videos where there's not a lot of speaking. I am hoping to build a bit more on text-rich videos first, so I do not plan to do actual video (image) processing any time soon.
I will keep that in mind!!
Re:Show HN: Summary Cat, a YouTube Video Summary Generator
on Friday September 22, 2023 @04:48PM (#37617569)
Hello! Thanks for the question. I do not myself restrict tokens/session. The model I am using GPT-3.5-Turbo-16k (https://platform.openai.com/docs/models/gpt-3-5), allows max 16,385 tokens in total per input/output.
So far, I found that each ~10 minute video uses around 1000 tokens. It costs me about 3 cents to summarize, which is not too bad as I don't have many users, and users haven't been requesting summaries for super long videos yet.
If this sites gets a lot of interest, I might start restricting something :)..
GPT 3.5 Pricing: https://openai.com/pricing
Show HN: Summary Cat, a YouTube Video Summary Generator
Hello HN!Please check out Summary Cat (www.summarycat.com). It uses OpenAI's GPT-3.5 to summarize YouTube transcripts.Please note that it only works for *English* videos right now.I used GPT-3.5 because GPT-4 is quite a lot more expensive (roughly 10X).I'd appreciate any feedbacks, criticisms, or feature requests.---------------------------Tech Stack - Frontend: HTML/CSS- Backend:...
Irreproducible Research in the AI Era (2018) [video]
Dataset Search (Google)
Data Falsificada (Part 1): “Clusterfake” by Data Colada
Harvard Fake Data Scandal Explained
Ask HN: Where to find free public datasets besides Kaggle/BigQuery/HuggingFace?
Scientists develop pill that destroys solid cancer tumours in early research
Tell HN: Tenorshare's “30-Day Money-Back Guarantee” Is Deceiving in My Opinion
Tenorshare says "30-Day Money-Back Guarantee" on its product page(1), which I interpreted as "guaranteed refund; no questions asked". However, it turns out that only limited cases like Duplicated Purchase will be refunded, according to its refund policy page(2).Am I right or wrong in thinking that they are trying to be deceptive? If so, what actions could I take to get my refund, if my reason...