owentbrown

Whoa. This looks both powerful and expensive.

My prediction is that, this time next year, top developers outside ai labs will be spending 50k USD+ on inference.

Within labs, I've heard spend is already far beyond this per developer.

I use AI to write documentation frequently. An AI agent, 600k tokens into a feature that it just authored, understands the feature as well or better than I do. It can document, compactly, what the code actually does, as well as the intent. These docs add value above having no docs and letting another AI, with zero context, read your bare code.

In the context in which I work, the quality of these docs is sufficient.

Unless your docs are being read by thousands of people, in 2026, in most contexts, handwriting docs adds less value than writing high quality instructions to your agent.

There are exceptions. For example, when kicking off a project, short crisp prose in a product brief aligns a team, removes uncertainty, and clarifies decisions. These are worth hand writing.

From your experience, is it comparable to Claude Code with Opus 4.8? How does it feel? How do the two differ?

This is what AI consolidation really looks like.

It's not an AI hacking into another AI's datacenter and shutting off the training. It's a slow concentration and slow alignment of power along one-party, national lines.

I've been thinking about how this will play out. I think there's a Lindy Effect. The longer the ban remains in place, the longer it's likely to remain in place.

I wish Linear would participate in FedRAMP. It's blocking adoption at my company.

Atherton has a *beautiful* public library adjacent to a defunct Caltrain station. It's great for kids and has a really nice cafe, ideal for VC meetings and networking.

Has anyone switched from Claude 4.7 Opus or ChatGPT 5.5 to this? How does it feel? Dumber? Worth it for the speed? I'd love someone's subjective take on it, after doing a long session of coding.

Reiner Pope gave a talk on Dwarkesh Patel about token economics. I guess faster is a lot more expensive, generally.

Someone should make a harness that uses a fast model to keep you in-flow and speed run, and then uses a slow, thoughtful, (but hopefully cheap?) model to async check the work of the faster model. Maybe even talk directly to the faster model?

Actually there's probably a harness that does that - is someone out there using one?

This is fun. Artsy, poignant, narrative. It reminds me of the fun internet, like in 2001.

Is anyone else noticing that the benchmarks for Claude 4.7 don't specify the token window? Cursor, and LiteLLM at my company, limit the token window to 200k.

It feels like to me like 4.7 is not better, and is maybe worse than 4.6 when capped to 200k context window.

Does anyone have stats on performance of 4.6 vs. 4.7 when context window is capped at 200k?

I really appreciate the author for writing this.

I learned years ago that I when I write code after 10 PM, I'm go backward instead of forward. It was easy to see, because the test just wouldn't pass, or I'd introduce several bugs that each took 30 minutes to fix.

I'm learning now that it's no different, working with agents.

When did white flour bread become a whole grain?

There's a picture of a loaf of bread next to the word "whole grains".