Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

genmon.github.io

Post reply on HN
Print view View original

31–40 of 177 posts

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#31

Post by genmon »

p0pcult wrote: post #30
genmon wrote: post #22

Some unlinked features... If you put the Dewey division in the URL, the directory auto-opens. e.g. here are episodes about prehistoric life (my current jumping-off point) https://genmon.github.io/braggoscope/directory#560 There's a visual map of episodes. After principal component analysis of the episode embedding vectors, these are the most significant two components as the x,y https://genmon.github.io/braggoscope/m…

Love the visual map. What does color mean? Any way to do a 3rd PC, and put the visualization in a cube one can toy around with?

Colour is the 3rd component -- I wanted to see the difference between overlapping episodes.

As for the 3D plot... here you go!

https://interconnected.org/more/2023/03/in_our_time-PCA-3D-p...

Basic PCA + Plotly is actually in OpenAI's official Python library (in `embedding_utils`) -- this plot is just the output from that.

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#32

Post by genmon »

CrypticShift wrote: post #29
genmon wrote: post #22

Some unlinked features... If you put the Dewey division in the URL, the directory auto-opens. e.g. here are episodes about prehistoric life (my current jumping-off point) https://genmon.github.io/braggoscope/directory#560 There's a visual map of episodes. After principal component analysis of the episode embedding vectors, these are the most significant two components as the x,y https://genmon.github.io/braggoscope/m…

Excellent! I'd love to see a script that sends a list of "descriptions" (1-100 words) to ChatGPT and directly gives you back a ready-made (embedding vectors closeness) map in a (textual) graph/chart format (like your above map or your plot https://interconnected.org/more/2023/02/in_our_time-PCA-plot... )

It turns out that "closeness" is usually hard to visualise/explore when you're dealing with a 1,000-dimensional space... and PCA has the failures mentioned above.

It's weird -- it's locally useful to navigate, and at a high level kinda useful, but only if you squint and don't look at the problems. So I feel like a fisheye visualisation would be appropriate? That's something that I'm exploring in other projects.

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#33

Post by genmon »

astroalex wrote: post #28

I love this project!! Ever since my partner and I discovered In Our Time a few years back, it’s been our go-to podcast to listen to together. Part of the allure is that the archive is so vast, but that makes it hard to browse. My partner made her own archive of In Our Time here, if you’re interested: https://shelby.cool/melvyn/ She used Wikipedia to find and categorize each episode. I also really like that she indexe…

No way! This is incredible. That h1 "Hello," Is the tagging manual? It's really good.

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#34

Post by genmon »

taberiand wrote: post #24
genmon wrote: post #15

Earlier quoted context omitted.

I've been considering this, but my assumption is that it would be tripped up by the specialist words. I wonder... is there a way to "prime" Whisper (e.g. with the embedding of the episode synopsis) so that it "listens out" for words related to a particular topic? I haven't looking but this would be neat!

I haven't tried, but the Open AI docs mention priming on the whisper model being available prompt string Optional An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

I hadn't noticed that, very much appreciated.

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#36

Post by genmon »

valgaze wrote: post #2

This is a really interesting use-case Applying "transformations" or classifying data in this way without having to setup a lot of detail-work seems like a real labor-saver/multiplier

I've started thinking about LLMs as a "universal coupling", if that makes sense? It's wild to be able to conceive of APIs to plain text, and natural language queries on structured APIs, but that's what we've got.

My mind was really opened by Nat Friedman's work in GPT for browser automation: https://github.com/nat/natbot

And of course using langchain/ReACT.

So different from ChatGPT and (imo) way more intriguing.

mentioned in this blog post: https://interconnected.org/home/2023/02/07/braggoscope

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#37

Post by genmon »

lerchmo wrote: post #23
genmon wrote: post #10

Earlier quoted context omitted.

One of the prompts is Extract the description and a list of guests from the supplied episode notes from a podcast. Also provide a Dewey Decimal Classification code and label for the description Return valid JSON conforming to the following Typescript type definition: { "description": string, "guests": {"name": string, "affiliation": string | null}[] "dewey_decimal": {"code": string, "label": string}, } Episode synops…

I like the typescript definition, rather than example json that I normally use.

Credit where it's due: I was working with structured data as JSON for the completion, and the Typescript definition hugely increased reliability. I took that from helpful advice (on Twitter) from Noah Brier who afiak came up with the approach:

https://brxnd.substack.com/p/the-prompt-to-rule-all-prompts-...

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#39

Post by gwern »

genmon wrote: post #32
CrypticShift wrote: post #29

Earlier quoted context omitted.

Excellent! I'd love to see a script that sends a list of "descriptions" (1-100 words) to ChatGPT and directly gives you back a ready-made (embedding vectors closeness) map in a (textual) graph/chart format (like your above map or your plot https://interconnected.org/more/2023/02/in_our_time-PCA-plot... )

It turns out that "closeness" is usually hard to visualise/explore when you're dealing with a 1,000-dimensional space... and PCA has the failures mentioned above. It's weird -- it's locally useful to navigate, and at a high level kinda useful, but only if you squint and don't look at the problems. So I feel like a fisheye visualisation would be appropriate? That's something that I'm exploring in other projects.

I wouldn't necessarily reach for PCA. No reason to think that the first two principal components necessarily encode anything particularly interesting. If you want to lay out each point in 2D in a way which keeps similar points nearby, something like t-SNE is worth a try - visualizing embeddings is what it was invented for.

Re: Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT

#40

Post by coder543 »

genmon wrote: post #15
specproc wrote: post #14

I love In Our Time, a real BBC gem. I've been meaning to pull all the audio for a while and this has inspired me. A fun thing to do would be to pass through Whisper, a great corpus to play with.

I've been considering this, but my assumption is that it would be tripped up by the specialist words. I wonder... is there a way to "prime" Whisper (e.g. with the embedding of the episode synopsis) so that it "listens out" for words related to a particular topic? I haven't looking but this would be neat!

In my experience, Whisper does a great job even with specialized terminology. It won't catch everything, but I think it will exceed your expectations. One of the hardest things about Whisper is choosing which model to use; they offer a variety of sizes, and sometimes the smaller ones do better than the larger ones. It's worth trying a few different models and deciding what is best for each particular application.

I will also say that I've personally been unimpressed with the new "large-v2" model, even though it supposedly scores better. The original "large-v1" model seems to work better than the "large-v2" model in the audio clips I've been testing Whisper against, but results will vary. In general, I find I'm really happy with what "small.en" and "medium.en" will emit, and they're much faster than the large models. (The ".en" models are specialized to English, and usually perform better for strictly English input, whereas the non-".en" models are trained on multiple languages.)

Post reply on HN