minxomat

Joined 10 years ago

Karma

3,195

Submissions

617

Member since

Sep 18

Blag: https://summarity.com, e-mail: hn [at] blag domain

Opinions are my own.

View on Hacker News

Recent submissions

Comment · 3 years ago

Experimenting with and/or reading about ChatGPT and then interacting with Siri feels almost offensive now. All of the assistants still suck - get on it AmaGooPple!

ThumbHash: A better compact image placeholder hash evanw.github.io

768 summarity 3 years ago 117 comments

Comment · 3 years ago

Is this related in any way to the actual ChatLLama project that is developed here: https://github.com/nebuly-ai/nebullvm ?

Comment · 3 years ago

The former. Makes sense for their business model.

Comment · 3 years ago

> The GPU version is commercial software. Please contact...

Shame.

Comment · 3 years ago

Some numbers here: https://github.com/qwopqwop200/GPTQ-for-LLaMa#result

Comment · 3 years ago

Follow up recommendation: for Spanish, “Madrigals Key” is language transfer in book form. It can in fact be used as a workbook for this course.

Comment · 3 years ago

Sure. Sent a ping.

Comment · 3 years ago

We're not far off: https://imgur.com/a/nJxxcUg

Comment · 3 years ago

A plot point in an episode of Person of Interest, where AGI "Samaritan" funds a charity (free tablets for students, Samaritan access pre-installed) to take over education and recruit more mercenaries.

Comment · 3 years ago

I'm building this, for (mostly) non-scientific non-fiction works (books, articles, news, etc.). Launching soon, with about 7,500 books indexed.

Generally, what I found useful to build a graph between "topics" or entities was to use a HyDE[1] prompt to generate possible distinct definitions and then build a nearest-neighbor network from that. This successfully identifies related concepts in the truly abstract sense rather than literal entities.

[1] https://summarity.com/hyde

Comment · 3 years ago

For me the hangup was always the hidden rule: host won’t open a door with a car. That is unstated and remains unstated even in modern discussions of the problem (see Pinker’s “Rationality”). Once explicitly states the outcome becomes intuitive.

Comment · 3 years ago

The whole point of the LLaMa paper is that large models are undertrained and oversized.

Comment · 3 years ago

A laptop and a desktop (Mac Studio)