naniel

oh man, the saga continues...

for those who need a primer on this: https://endash.us/toolkit/items/mini-shai-halud (yes an ai-assisted build obvi, but not just an ai blog)

really cool looking. i'll let you know if i end up cloning and trying it out, but the animations that show it make it look really smooth. nice to have things like this to potentially integrate into other oss projects

i'm a big fan of web-native books, and I think they can live neatly alongside epubs and print copies. these two are some of my favorite

https://practicaltypography.com/

https://www.stripe.press/poor-charlies-almanack

OpenAI's release explicitly says No. But then also caveats that with "we cannot rule out that de-identified data derived from their usage of our products" impacted things. What's most striking to me, and what may or may not be true, is the "we cannot rule out" bit.

"We (the researchers and the agents) did not see any of their work through any means until they released it publicly — in particular, no specific user data was accessed in order to solve this problem. While unlikely, we cannot rule out that de-identified data derived from their usage of our products helped improve our models . However, our proofs differ significantly and even the precise results proved are different in the Euler case (forced vs unforced)." https://openai.com/index/navier-stokes-solution/

NOTE: there are a couple duped threads around this. i replied on a different one first before seeing this one

OpenAI's release explicitly says No. But then also caveats that with "we cannot rule out that de-identified data derived from their usage of our products" impacted things.

What's most striking to me, and what may or may not be true, is the "we cannot rule out" bit.

"We (the researchers and the agents) did not see any of their work through any means until they released it publicly — in particular, no specific user data was accessed in order to solve this problem. While unlikely, we cannot rule out that de-identified data derived from their usage of our products helped improve our models . However, our proofs differ significantly and even the precise results proved are different in the Euler case (forced vs unforced)." https://openai.com/index/navier-stokes-solution/

agree with this. i don't see the point of the terrarium if the fly never moves or really changes at all, other than seeing to twitch faster when sugar is on.

Such a fun story included here. It'd be great if this was also in a native web-app ebook too (i know it's harder to charge $ effectively, but most people end up wanting the physical or epub (for their e-reader) anyway if they like it.

"The [benchmark] we deserve, but not the one we need right now."

Answers a simple question: Is a hot dog a sandwich? Pings the major models for a one-word answer, and generates reports accordingly.

Silly, stupid, whatever. But it's open-source and able to be cloned/forked to answer your "real" questions with ease.

Oh, and you can submit your own questions to be added to the list.

Built with assistance from n-dx

I was really hoping this would be about 12-factor authentication

The arms race continues.. we do need to keep trying to crack down on the bad actors, but it is only going to get worse

For those who aren't familiar with teamPCP's big attack recently, we made a Scroll to highlight how it was so effective: https://endash.us/toolkit/items/mini-shai-halud

CI/CD, rollback strategy, blue/green deployments, testing regions, automated testing suites... you need all of this and more.. because code reviews just aren't going to be happening soon. luckily, these LLMs can help in building that infrastructure needed to reliably ship changes quickly

There are a lot of systems at play here, and those things don't change overnight. I think certainly we'll look back in 10 years and clearly see this was the start of a revolution, but we seem to have a distorted view of what a revolution is. The industrial revolution didn't happen overnight, and many folks during the time didn't have any concept of what was actually happening.

Classic hindsight bias.. And it's funny that Sam is saying this.. just a few months ago i saw his interview where he claimed to be very good at seeing the future and predicting what will happen

Love the motivation behind this, and I think the execution is really quite nice. I really enjoy these little learning games/apps -- i think it's a great way to be using AI for development

No it's not slowing us down at all. For fresh codebases it's several orders of magnitude faster, but also for legacy/existing codebases it has been a BOON to our development.

First thing we do is to map out an existing codebase (or a piece of a codebase if it's a monorepo). We have the models synthesize what's in there and document the architecture AND the intent of the app (retroactively building a PRD based on codebase). We use n-dx for this and it has worked very well. There's still bugs and plenty of improvements to be made with the tool (n-dx), but it's open-source so it's easy to make improvements whenever it falls short during a set of tasks

Fable is quite good, but i also noticed that the later opus models don't seem quite as effective as before.

We break down our tasks pretty granularly before they get picked up by a model, and for that workflow we've found that sonnet 4 and opus 4 are still quite effective, and debatably more effective than the 5s

for reference, we use n-dx (https://n-dx.dev) for our workflow

Nicely done! Seems like it's almost responsive, but I'm unable to see the latex preview on mobile

I first experienced the Beer Game in school, played physically. Loads of fun, with people getting all angry at each other, throwing blame around, "why the heck did you order so much??" etc. It was crazy to see how quickly the whole supply chain fell apart

It taught me a ton, and I wanted to take a stab at making a free online version of it

This is meant to mirror the classic MIT game as closely as possible, but able to be played remotely and by anyone who has the link

Anyone can play a full round right now, with no signup required. If you're teaching a class or running a workshop, a free En Dash account lets you host sessions (and you get the full debrief/readout persisted to your account)

Built by me, with some help from other folks at En Dash Consulting.

Play a round and let us know what score you managed :D Would love to hear any thoughts!

sounds neat, and the disclaimer is appreciated. a simple recording or other visual walkthrough would make it a more compelling download

looks like great performance.. how does one buy/use this? every ~6mo i go looking for good eink monitors/devices, but am regularly disappointed

awesome breakdown of the process you took. reverse-engineering is crazy now with AI. IP is dead

this also reminds me of what got me hooked on CS in the first place: a simple java steganography app in cmsc150

this is cool. the Manuscript part of the UI is a little bit buried imo, but i really like the concept and it seems to work pretty nicely. what AI are you using in the background (subject says claude code, but curious what's behind the scenes)? how are you allowing un-auth'd users try this?

hadn't heard of Fossil, though i love the name. but why use this instead of git?

thanks for sharing. this is definitely a nuisance currently, and i like how simple your solution is

devs stay getting wrecked by these supply chain attacks. i know mini shai hulud continues to resurface in the node community https://endash.us/toolkit/items/mini-shai-halud

very neat, and appears to be well-built (haven't found any glaring bugs :D ). you might be able to get even more interactive with the canvas somewhat easily by using html-in-canvas instead of React Flow, or in addition to.

https://html-in-canvas.dev

Interesting list! I really enjoyed "The Square and the Tower" by Niall Ferguson. Not exactly in the same realm as these, but pretty close and definitely eye-opening