eob

eergisterendiscuss

Simon I hope from this day hence, your bio always includes:

"Simon Willison, among other things, is an advocate for the inclusion of pelican geometry in LLM training datasets."

eob

vorige maanddiscuss

I think because you don't know /which/ developer you're going to get.

One interesting aspect of LLMs is that each one, weights frozen, can be thought of as a single developer whose work you have already evaluated.

The cost of finding, evaluating, and negotiating with a new human is tremenous.

eob

2 maanden geledendiscuss

These comments are so filled with cool projects and visualizations I’ll throw my own out there:

Trying to generate non-slop, print-worthy recipe books for different diaspora communities.

www.robotbookclub.com

I’m pretty sure the recipes have surpassed slop. The photos are pretty close. The layouts, intros, and “chef photos” need a lot of work though.

eob

2 maanden geledendiscuss

This is how I write down recipes for myself! There’s got to be some cognitive archetype that works better with this style encoding.

eob

2 maanden geledendiscuss

Do you have any suspicion about what is different between the backends?

That's an absolutely bonkers statistic: it would mean spurious differences in hosting container overwhelm the performance differences between models.

eob

4 maanden geledendiscuss

My guess it's just the emergent behavior that results when a company doesn't provide developers time to fix bugs.

If their week is already booked full just trying to keep up with the roadmap deadlines, a bug ticket feels like being tossed a 25lb weight when you're drowning.

You could say: "but have pride in your work!"

But if your company only values shipping, not fixing, that attitude doesn't make it through the first performance review.

eob

6 maanden geledendiscuss

You think like a person who’s debugged large systems failures before :). That feels very plausible.

eob

6 maanden geledendiscuss

Some outlets reporting T-Mobile and ATT as well.

I assume state on state cyber attacks are commonplace but get minimized to avoid public fear.. perhaps this will be the first notable one.

eob

7 maanden geledendiscuss

I build coding agents for a living, and I'm struggling to map this onto the set of things I do at work.

In general, interoperability and user choice are really important for us to get right as the community of people building AI platforms...

Have others reading this document been able to map it onto their work?

As a specific example:

> ai://bank/service/payments?amount=10&currency=USD

I'm not sure what this is representing here. Is it a way to encode a clickable link to chat with `bank` about `service/payments` with a few additional args attached?

eob

vorig jaardiscuss

Third party apps can’t use the network though. Iirc there’s an async message queue with eventual delivery that each app gets, which it can use to send messages back and forth with a paired phone app.

eob

vorig jaardiscuss

Bravo -- this is fantastic.

I've been waiting for this ever since reading some interview with Orson Scott Card ages ago. It turns out he thinks of his novels as radio theater, not books. Which is a very different way to experience the audio.

eob

vorig jaardiscuss

Or vice versa - perhaps some subset of the "thought chains" of Cyc's inference system could be useful training data for LLMs.

eob

vorig jaardiscuss

An aspect of these self-improvement thought experiments that I’m willing to tentatively believe.. but want more resolution on, is the exact work involved in “improvement”.

Eg today there’s billions of dollars being spent just to create and label more data, which is a global act of recruiting, training, organization, etc.

When we imagine these models self improving, are we imagining them “just” inventing better math, or conducting global-scale multi-company coordination operations? I can believe AI is capable of the latter, but that’s an awful lot of extra friction.

eob

vorig jaardiscuss

Are you comfortable sharing the video & lip-sync stack you use? I don't know anything about the space but am curious to check out what's possible these days.

eob

vorig jaardiscuss

This looks fantastic — congrats on the launch.

As an armchair observer, the agents + browser space feels like it’s waiting for someone to make the open source framework that everyone piles on to.

Proxy rotation sounds like a solid way to monetize for businesses.

eob

vorig jaardiscuss

There was an SF office of 18F -- IIRC it was in the building to the right of the Civic Center park as you looked at it from the Bart stop. They were great folks from every encounter I had with them.

eob

vorig jaardiscuss

Let's presume this gets developed to ShadCN/Tailwind level quality.

In that world, what would be the tradeoffs between:

- NextJs + Tailwind + ShadCN

- NextJS + ?? + Shoelace

I don't have a good sense of how web components compare to practice of "copy-by-value, then compile-into-binary" UI shipping that's common in the Next + Shad world these days.

eob

2 jaar geledendiscuss

Have you ever managed a complex, dynamic, changing system and found that the optimal size based on current conditions was 20% less than it was at some prior time?

I can think of all sorts examples.

eob

2 jaar geledendiscuss

So GCS customers will trust their codegen product. (Engineers aren’t the buyer; corp suite is)

eob

2 jaar geledendiscuss

A Project Jengo grant for using Agents/LLMs to identify prior art could be a fantastic experiment..

Submissions

What I learned building an AI book publisher

Ask HN: What policies should Sachs pursue as the new US AI and Crypto czar?

Show HN: An AI street hawker that negotiates and sells licorice

Show HN: Open-Source AI Adventure Game

One click Auto-GPT Telegram bot with source

Kube Inject Monitoring

Turn your video course into a chat bot

We built an exceedingly polite AI dog that answers questions about your APIs

Show HN: Ask the Pandas Documentation

Drop-in endpoint observability for Docker and K8s

Show HN: Vercel and LangChain Templates

Show HN: Hosting for LangChain APIs

Show HN: Deploy Button for GPT-3 API Back Ends

[untitled]

Show HN: Insults as a Service

Shipped with AI – Weekly, focused AI commentary for builders and investors

Show HN: An adaptive Chinese reader. Only helps where you need it

We stay productive as a remote-first startup

Steamship: Heroku for Language AI

A text alignment algorithm inspired by.. soap operas?

comments