npollock

exactly, it's like Bobby Fischer playing 10 games of chess simultaneously

one of the interesting properties of public forums like SO is that the maintainers of software packages get visibility into the problems and frustrations that their users experience

we're losing that signal when the Q&A behavior shifts into language models

learn by considering critique

You can configure the status line to get a feel for token usage:

[Opus 4.6] 3% context | last: 5.2k in / 1.1k out

add this to .claude/settings.json

"statusLine": { "type": "command", "command": "jq -r '\"[\\(.model.display_name)] \\(.context_window.used_percentage // 0)% context | last: \\(((.context_window.current_usage.input_tokens // 0) / 1000 * 10 | floor / 10))k in / \\(((.context_window.current_usage.output_tokens // 0) / 1000 * 10 | floor / 10))k out\"'" }

Disney said "Our IP is $1B for a 3yr license, or we sue"

Altman said "We can pay with equity, but let's frame it as an investment"

No cash exchanged

it could be the "grounding with google search" feature when using Gemini models

no, but a subset of English could be

LoRA adapters modify the model's internal weights

Here's how I would market this:

Create "packages" of context for popular API & Libraries - make them freely available via public url

Keep the packages up to date. They'll be newer than the cutoff date for many models, and they'll be cleaner then the data a model slurps in using web search.

Voila, you're now the trusted repository of context for the developer community.

You'll get a lot of inbound traffic/leads, and ideas for tangential use cases with commercial potential.

Are 7 free weekly eval runs fair compensation for sharing your evaluation and fine-tuning data with OpenAI?

"The takeover of io will provide OpenAI with about 55 hardware engineers, software developers and manufacturing experts"

6.5B / 55 = $118 million per engineer

not a cheap aquihire

if you own the device, you control the flow of data and dollars

something like this that runs as a browser agent, allowing me to extract structured data from websites (whitelisted) using natural language queries

A quote I found helpful:

"reinforcement learning from human feedback .. is designed to optimize machine learning models in domains where specifically designing a reward function is hard"

https://rlhfbook.com/c/05-preferences.html

does the tool snap to I-frames when slicing?

how long before the advertisers pressure model providers to "fine-tune" mentions of their competitors?

doesn't Stripe have an interest in maximizing this revenue recovery? they earn a percentage of successful charges

running inference

thanks - is there a way to determine/monitor if excessive swapping is taking place?

you're right, Firefox is gobbling up about half of the RAM

thanks for pointing me in this direction

thank you, disabling the floating thumbnail has sped up the file/image delivery

the launchctl analysis is a great suggestion too

OpenAI gets the data it needs, and publishers get prominent placement in the product:

"PPP members will see their content receive its “richer brand expression” through a series of content display products: the branded hover link, the anchored link and the in-line treatment."

There's some similarity to the search business model

are there any open source solutions in this space? something that sits in front of your API as a proxy, and has an interface for managing access, rate limits, billing etc - with simple deployment to a cloud provider?

your values change as you age, so if you're repeating the same old activities and feeling drained - it's time for change

recall the excitement you had as a child, as a teenager, a young adult - this will yield clues as to what might spark your energy again

as others have mentioned, movement and exercise are simple hacks to improve mood quickly