I got Opus to knock out an MCP server that implements subagents running in pi and tell Opus to send work to DeepSeek. Or I tell it to ask GPT-5.5 for critiques. It's manual but saves a lot of tokens.
I was thinking about inhouse model inference speeds at frontier labs like Anthropic and OpenAI after reading the "Claude built a C compiler" article.
Having higher inference speed would be an advantage, especially if you're trying to eat all the software and services.
Anthropic offering 2.5x makes me assume they have 5x or 10x themselves.
In the predicted nightmare future where everything happens via agents negotiating with agents, the side with the most compute, and the fastest compute, is going to steamroll everyone.
I'm building my take on a low-touch task completion assistant designed to counter distraction and hyper-habituation.
It's starting off as a MacOS app because that's the machine I have. I didn't know Swift or SwiftUI when I started. I now know them somewhat, but the entire app has been vibe-coded. This has made it slow going. Very "1 step forward 2 steps back" until I switched from Claude Code to Codex and GPT-5.
I'm hoping to start an initial beta within the family in the next week or two, and then a wider round in January.
Are these numbers full time employees only or total FTEs? Because it mentions Walmart: "Walmart’s full-time employees number remained relatively constant for the last 10 years".
Would revenue / person-hour show a different trend? Because there are a lot of part-time and contract workers out there.
You might be how surprised how low a dose you need for an effect. 5-10ug of Ritalin noticeably reduces the "noise floor" for me.
How do you take 5-10ug? Dissolve 10mg in a litre of something. Get a 1ml dosing syringe. It has 0.1ml markings.
You could start there and increase it until you find what works. Also, if you take very little you can have a break on weekends and not suffer too much while remaining sensitive to lower dosages.
All rights reserved. No part of this publication may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the publisher, except as permitted by U.S. copyright law.
“Reproduced” and “electronic” are the relevant terms here.
I remember when gpt-3 came out and you could get it to spit out chunks of Harry Potter and I wondered why no-one was being sued.
The models are built on copyright infringement. Authors and publishers of any kind should be able to opt out of being included in training data and ideally opt-in should be the default.
And I hope one day someone trains a model without the use of works of fiction and we find a qualitative difference in their performance. Does a coding model really need to encode the customs, mores and concerns of Victorian era fictional characters to write a python function?
Gave it a try. After a few minutes I felt more like I was recognising the samples than I was recognising the notes. Not sure what you can do about that short of physically modeling an instrument.
People out there trying build some semblance of AI out of an LLM using larger and larger networks of “agents” that generate, classify, revise and verify data using the same LLM they're building larger and larger networks of agents upon to try and build some semblance of AI.
The end game is a brain-sized network where each neuron is an agent sending a 1M token prompt to a 10T parameter model to update their "weights".
I've never seen this before. I love the design. It's like a drum machine for spreadsheets. And it's from 1983, the same year the Tandy Model 100 was released. A good year for gadgets.