avindroth

Could you share the code for some of the custom threading macros you created? Looks very useful.

Tacit programming + llm control library (like LangChain) has a lot of untapped potential. Tacit programming shines when the control structures are simple (and functions/variables can be anonymized), and these patterns occur frequently in programming on top of llms.

For those who have the book, what is contained in the "discussion of the interactive Lisp programming process" as mentioned by Paolo?

Forth really changed the way I think. I now take notes in a Forth-like way. Very underexplored.

In my experience, perfectionism is crafted post-procrastination. It probably makes no sense, but the mind often does this convoluted thing in order to protect procrastination.

No, but there should be. If interested in collaborating (I made ChatGPT.el), shoot me an email at [email protected].

https://github.com/joshcho/ChatGPT.el

Agreed. Our computers are so powerful, do we really need this additional complexity?

And of course, if performance becomes an issue, we can make minor improvements then.

There’s a concatenative languages discord btw. Email/msg me joshcho @ stanford or @eating_entropy

Literally everything was happening on Twitter.

From spaces to “OpenAI is nothing without its people” to heart emojis.

Sam and Greg posted their statement there.

This is a huge win for Twitter.

Satya wins by letting Ilya win. Wow.

Why do you think people undervalue it? Very curious.

Yeah. pg/chesky/masayoshi must be really dumb or sth.

Are you participating in AoC maybe? I might write some stuff.

In terms of speedrunning, couple of friends and I are trying to speedrun AoC using LLMs (sacrilegious i know).

It’s been growing a bit; if interested, feel free to shoot me an email to [email protected]

Or @eating_entropy on X

Hey Victor, these are amazing tips. I am currently building a DSL for LLMs, and would love your feedback/consulting. I could not find your email online.

Please feel free to reply to this or reach me here: @eating_entropy on X [email protected]

Would love advisement from someone who has thought about DSLs extensively!

I emailed at [email protected] (as shown in the website), but the email account doesn’t exist.

pls include the url to ur site!

Sent an email. You guys should make it obvious it’s reframe.is, not reframe-ai.com which is first on search

Carson Gross

https://www.backendbanter.fm/episodes/024-behind-htmx-carson...

Tiered rollout, not getting April 2023 on both of my accounts. Also saw September 2023 on Twitter.

John Ousterhout, Carson Gross (htmx, https://grugbrain.dev), and Rich Hickey are my favorite people on complexity. John Ousterhout was notably my professor for operating systems @ Stanford. He taught not just ways to design software, but also ways to live.

Carson’s work is also directly influenced by Ousterhout, as referenced at the end of his article.

For John Ousterhout, I suggest looking at the class website: https://web.stanford.edu/~ouster/cs190-winter23/

For Carson Gross, I suggest his book, Hypermedia Systems: https://hypermedia.systems/

1. I don’t think it’s too hard to understand BYOK or n number of tokens. I’ll have to talk to the market at large but personally, pretty clear.

2. Maybe you can suggest an alternative?

Well, this is just clickbait. Choose boring technology means sth pretty concrete for someone without context. It’s not that you can’t reasonably title it. It’s that you can’t reasonably title it to generate views.

I understand the sentiment, but then one should expect criticism of the schism between title and content.

I expressed myself too succinctly and without context, sorry.

I meant we need a new DSL better suited for prompt engg, and a UI that better supports longer strings. Actualy this UI can be something compatible with Python.

But overall a reimagination of the dev experience is what I am getting at (like Jupyter for LLMs).

Dm me @eating_entropy on X for more.

We need a new language/DSL. Python is a lost cause for strings as first-class.

Hi all, my friend (https://twitter.com/yashsavani_) and I (https://twitter.com/eating_entropy) decided to turn our FB conversation into a substack essay. It actually turned out to be much better than we expected. Claude 2 is surprisingly good! Way better than GPT-4, which sounds like a high schooler. Will post some instructions on github later as to how to replicate.

It’d be cool if it acted against Github repos, then you can save the embeddings and have a unified interface for querying repos.

I had this problem trying to learn a library and figuring out what all the functionalities are. I ended up making a non-ai solution (an emacs pkg), but this seems just a step or two away from your current project imho.

This space is surprisingly under-explored. Any idea in this space is basically new.