GrugNotes

I was so grumpy today. Planning with Opus and codex took so much longer to float the right solutions.

I’m tired of living in unprecedented times

🍒

Has @tferriss never listened to @AcquiredFM

Fast things are nice

Fable is a good model. As with all new models, it is simultaneously excellent and entirely unremarkable (relative to other models). It is slow and expensive, and the "loops are all you need" discourse they are pushing is obvious in the context of someone using Fable-class models What I've found so far is that for broad scope design (code architecture) tasks, Fable is unremarkable. Or, not better enough to justify its cost and speed. But in highly targeted goal-oriented loops, it is another beast entirely. It is very slow but produces very good results. I let it churn on optimizing a SwiftUI-layout resolver in Go I wrote and it was able to bring it down to an order of magnitude I could not reach myself (micro => nanosecond scale). But it took 2 hours and $40 to do it and I had to claw back some changes it overfit to Apple Silicon. Still, very worth it. In comparison, for "implement this feature/change" iterative work, I ran head-to-head Fable vs GPT5.5 vs. GLM-5.1. They all produced equally acceptable final results, but GPT5/GLM did it in a couple minutes and Fable was churning away for 40 minutes. And GLM cost me less than a dollar, GPT5.5 ~$1.50, and Fable cost $9. You can see that in this context, interactively working with an agent is nonsense. Its too slow. You need to write loops to keep the agent working and you probably want to highly parallelize the work being done. As with all things, I think a balance makes sense... My sense is that I'd reserve Fable for targeted, surgical analysis and work. Not for daily driving everyday tasks. I'm going to keep spending a shitload of money (relatively) and maining Fable for the rest of the week to continue to judge, will report if anything changes. I'll continue to head-to-head as well.

So I just scheduled codex to start Claude back up when my credits are back. 😴

Grug Notes can do this btw

Never mind paying for food and rent. I need to launch and make money so I can afford Claude in a couple weeks.

@theo It's smarter than most people I know, including me.

Half way there.

@annieqyang Yes

hot take: there are too many tech ppl building for other tech ppl here it's time we (esp ladies) build what the general population needs what are you working on that moves the needle?

@mustafasuleyman Nice

My weekly sleep schedule is like 10, 10, 10, 4, 4, 6, 7.

@sundeep Can we have it on groq?

Nemotron 3 Ultra stands as the most intelligent open-weights model ever shipped by the United States. NVIDIA provides the weights, data, and recipes for Nemotron 3 Ultra.

Oh wow

@htmx_org I mean great minds…

lol

@NotionHQ Sure I’m fine with that, just send me all the people that just want a notes app. And we can be best bros!

@GrugNotes Your long lost brother?

Wait what is this lol.

@rheum_ai @usgraphics @NotionHQ True true

@usgraphics @NotionHQ Actually, this is the original Grug.

Meet Grug. Grug is a “Caveman Designer” Custom Agent that our team turns to for blunt, anti-complexity product/design feedback. Basically: “complexity bad, make simple, make button look like button.” Here’s what Grug said about a recent All Hands.