HackerTrans
トップ新着トレンドコメント過去質問紹介求人

skramzy

no profile record

投稿

Show HN: Openloom – Turn Loom links into transcripts and frames an LLM can watch

useopenloom.com
3 ポイント·投稿者 skramzy·2 か月前·0 コメント

Anthropic's official plugin gets the core principle of the Ralph Wiggum wrong

github.com
1 ポイント·投稿者 skramzy·6 か月前·1 コメント

Yelp Is a Full Featured, Unhinged Boomer Social Media Platform (2024)

poorlyideated.com
6 ポイント·投稿者 skramzy·昨年·4 コメント

Inspired by a recent post, an old-timey radio station for my wife's newsletter

revopsradio.com
2 ポイント·投稿者 skramzy·2 年前·1 コメント

コメント

skramzy
·3 か月前·議論
Neat!
skramzy
·3 か月前·議論
What's TDS?
skramzy
·5 か月前·議論
lmao
skramzy
·6 か月前·議論
Anthropic's official ralph plugin gets the core principle of Ralph wrong by preventing a single instance of claude from exiting, rather than continuously starting new sessions.

Here's an opinionated, but proper implementation of the Ralph Wiggum AI technique.

Ralph solves the AI context window problem in the most simplistic way possible; keep feeding new AI sessions the same prompt until the job is done.
skramzy
·6 か月前·議論
> Sorry, that's AI. So is OCR, so is voice recognition, and many other things you probably use and take for granted

Have you heard of machine learning?
skramzy
·8 か月前·議論
That's Stripe's transaction fee, not theirs
skramzy
·昨年·議論
I had a lot of fun writing this. Fascinating stuff.
skramzy
·昨年·議論
It definitely does not
skramzy
·2 年前·議論
[flagged]
skramzy
·2 年前·議論
I'm not sure how they built theirs, but here's how I built mine:

- Parse the newsletter RSS feed - Summarize the most recent post with an LLM in the style of a fast-talking 1920s transatlantic radio broadcaster - Generate an audio file by synthesizing a custom voice I generated by sampling the recap narrator of Avatar: The Legend of Korra - Upload the file to a cloud object store and return the playback URL to the client - Repeat steps 1 - 4 each week until the heat death of the universe

This will run autonomously with new weekly content for as long as the newsletter persists.

Built with Next.js, TypeScript, Tailwind & Vercel
skramzy
·2 年前·議論
What gets measured gets optimized