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

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

Lol now this is the kind of benchmarking i'm looking for

Thanks for the clear guide! Brief but explanatory.. Gonna have to make some time to try this out

Eeee this is very fun. love that I can play without signing in too

i agree with this.. but also think it could stress a couple things more:

- satisfying the needs of parallel agentic development is wholly aligned with the optimal DevSecOps CI/CS/CD WhateverTerm models out there. And that's rad, bc a lot of orgs have a reference frame to map to.

- microservices, monoliths, monorepos, mammoths, whatever.. The code and services can be structured however, so long as the release capabilities are modular and governable/manageable/auditable/flexible/transparent/etc. A killer workflow allows for tight independent releases, but not chaotic, with proper add'l structure/scaffolding to satisfy that list above. Microservices and smaller repos can help with the context window bit initially, but you can rig up and kind of local llm-focused setup to allow for selective context and holistic context (across N repos or N projs within monorepo)

- strategy: use the robots to fix the problems in your PDLC/CICD/ABC so that the robots can help you out more, and keep iterating on that

this is hilarious.. love it. Reminds me of Zoolander lol

i also did something similar with a learning game for kids, where moving the car requires typing in the correct keys on the keyboard.

oof, not rust too. this has been brutal for the node ecosystem, hopefully cargo also gets the proper controls to help avoid this, like the in-flight min-publish-age

we put together a Scroll on how this manifested with node, if anyone finds it helpful to understand that attack vectors & mitigation steps: https://endash.us/toolkit/items/mini-shai-halud

thanks for open-sourcing this too. fun experiment. i'm thinking i might try to tie in the html-in-canvas spec to see how it leverages that on top of just the art

we definitely do

i don't think there'll be a drop in demand, but with supply chains.. beware the bullwhip effect https://beergame.endash.us/bullwhip-effect

this is really neat, and i look forward to diving in more. i've built a couple different Mermaid-related apps/plugins, and i think the wysiwyg you implemented here is pretty clean. nice work!

and glad that this led me to OpenKnowledge.. hadn't seen that before

this is an important topic, and i hate that people forget how difficult it is. in any political conversation, it's pretty easy to pull this thread to unravel anyone's adamant belief in one thing or another (e.g. gun control). my biggest concern is that people seem less willing than before to actually have those discussions.. they'll immediately just label you as being opposed to their views, "against" them.. when really we need these conversations to find viable policy solutions that wont easily be used in the exact opposite way that they were intended when implemented