News for hackers. Stuff that matters.

karfly

tl;dr:

1. Copy the ChatGPT share link

2. Prefix with "pdf": "chatgpt.com/share/..." -> "pdfchatgpt.com/share/..."

3. Instantly get clean PDF, Markdown, or HTML

Story: I often share ChatGPT dialogs with colleagues, but share links usually fail: loading issues, cookie popups, or temporary access. PDF/Markdown sharing solves this completely for me.

Existing Chrome extensions generate messy PDFs and aren't mobile-friendly.

So I built a reliable ChatGPT-to-PDF exporter, spending a fun week reverse-engineering OpenAI APIs and vibing on the PDF readability and design. The app handles code blocks (with wrapping), LaTeX, long tables, inline citation links, images, emojis, special symbols, and more.

It also generates Markdown for easy dialog copy-pasting into Cursor or other tools.

How to use:

A. Go to pdfchatgpt.com and paste your ChatGPT share link

B. Use URL prefix lifehack from "tl;dr" section above

Feel free to report edge cases or parsing errors in the comments.

And it's free.

pdfchatgpt.com

Ask HN: Optimal video render settings for Instagram uploads?

I'm developing a video editing app for iOS and have faced an issue with video quality on Instagram. While exported videos play with high quality on my video player, uploading these same videos to Instagram (including Stories and Reels) leads to a significant loss in quality.Does anyone have recommendations for the most effective render settings to maintain video quality on Instagram? I'm...

( Read More... | no comments | 2 points | on HN )
Re:Donate.md – Crypto donation page for your GitHub on Tuesday August 29, 2023 @07:32AM (#37306176)
Using such donation page I managed to collect $2K+ donations for repo: https://github.com/karfly/chatgpt_telegram_bot.

I'd be happy if this helps anyone!

Re:ChatGPT recreated with GPT-3.5? on Wednesday January 18, 2023 @01:56PM (#34431192)
IMO all RLHF stuff is mainly about aligning model not to reply with offensive and inappropriate answers, but NOT about making model's answers better.
Re:ChatGPT recreated with GPT-3.5? on Wednesday January 18, 2023 @01:44PM (#34431002)
You're totally true. But it turned out, that proper prompting (like packing dialog context into the prompt) worked great.

I spent many hours with orig ChatGPT and with this recreated version. The main difference I have found is that the recreated ChatGPT is more inclined to ask questions on questions (maybe can be fixed with more prompt engineering). I didn't find any major differences in the quality or usefulness of the answers.

Re:ChatGPT recreated with GPT-3.5? on Wednesday January 18, 2023 @01:34PM (#34430860)
It's true – you need to pay for OpenAI API. With my typical usage frequency of ChatGPT it's going to cost me about 3$/month.
Re:ChatGPT recreated with GPT-3.5? on Wednesday January 18, 2023 @01:17PM (#34430584)
1. You’re right, it’s not ChatGPT exactly. ChatGPT = GPT-3.5 + finetuning on conversational data + alignment (RLHF). But I found out, that GPT-3.5 + proper prompting gives comparable results and works really good.

2. The context of the conversation is preserved by adding whole (or some parts of) dialog to the prompt.

Re:ChatGPT recreated with GPT-3.5? on Wednesday January 18, 2023 @12:45PM (#34430093)
We all love chat.openai.com, but...

It's TERRIBLY laggy, has daily limits, and is only accessible through an archaic web interface.

This repo is ChatGPT re-created with GPT-3.5 LLM as Telegram Bot. And it works great.

In addition it supports special modes like "Code Assistant" and "Movie Expert".