1. The end of unlimited token subsidization and a new status quo of metered usage limits.

2. Adding to the above, self-initiated usage limit resets give you some control and again help lessen the sting of the end of subsidization.

Right now though, I think Anthropic and OpenAI are in open MAU war ahead of their respective IPOs and that might be a bigger factor.

The culture leaned heavily toward 996: 9 a.m. to 9 p.m., six days a week. I was there during a particularly tumultuous period, and by that point a lot of the staffing had already been hollowed out.

That said, the OnePlus 11, 12, 13, and 15 are great phones. The 13 and 15 in particular have insane battery life. I have never managed to drain either one to zero in a single day.

As far as I know, OnePlus and Motorola are also the only major companies selling phones with silicon-carbon batteries in the United States. It is ridiculous that Samsung and Apple still have not adopted them.

One of my biggest frustrations at OnePlus was how much of the internal tooling remained in Chinese or used poor English translations. Most of the management was also based in China and often did not seem to understand the US market very well.

Probably the most ridiculous example was an internal invoice or payment-submission portal. It was awful to use, but the terminology was even stranger. A submission apparently needed to be “signed” and then “sealed.”

I never asked anyone what the original Chinese term was, but I assumed it referred to the use of a Chinese name chop or company seal. Name chops are stone stamps bearing a person’s or company’s name that are pressed into ink and applied to documents as a form of authorization.

It was a small thing, but it captured the broader problem pretty well: internal processes designed around Chinese business practices were translated literally and then handed to US employees with very little localization.

I have struggled with on-and-off sleep issues for a while, and I'll admit I don't always follow perfect sleep hygiene. But there is something about dumping my thoughts out loud that completely shuts down the repetitive, circular thinking that usually keeps me awake.

It would be like how Ozempic lead to a mysterious quieting of Body Positivity/Health at Every Size advocates. They were a vocal minority, there was much "debate" and cri de couer from many sides and now its all evaporated without a farewell or explicit winding down.

And if you made it through all 99 beers on their list, you got a small plaque on the wall, about the size of one of those e-ink grocery price tags. It was a great tavern-like atmosphere, and the kind of place that felt increasingly rare even before it was gone.

The other thing is I will ask an agent via Telegram to code stuff, so I want an agent that is smart enough to do it all. I prefer brute forcing with money right now. I hate when LLM make bizarre mistakes, I end up spending way too much time figuring out the issue.

I use Openrouter, so hopefully no one has built a perfect replica of me in their storage. I flip between models too.

But to be clear, I am living dangerously with agentic workflows in general. Haven't been burnt yet (other than accidentally running up a huge Gemini bill which made me switch to Codex Oauth and Openrouter for cheap Minimax 2.7)

I am moving to a commander/orchestrator model to use both frontier and cheap models and eventually a better local LLM once I buy a 5070 Ti, 3090, 64GB Mac M1 Max, 128GB Strix Halo (probably missed that train) or the AMD R9700.

It would have been hilarious if the author spoke like a caveman in his video or had a section in that article where he explained his conclusions like a caveman.

Storing my Health Insurance's Member ID, RxBin and other data. Recording the serial number of a product I will be calling technical support for. Organizing files to be more logical and deduplicating or consolidating as needed.

Whenever I want this info, I'll just ask my LLM to pull it up.

At least, that's my theory.

The big advantages of local on a business level are:

- Freezing your model's exact settings once you've locked in some kind of workflow that works just fine. - Guarding against insane token usage from LLMs who have been told to never stop until they figure out the solution OR setting up an LLM run incorrectly. (The last one happened to me with Gemini 3.1 Pro) - PII or some need for on-premise only LLMs.

I've switched away from Gboard to Futo on Android and exclusively use MacWhisper on MacOS instead of the default Apple transcription model.

Need to disappear? Just go to the Gathering and find your new family. Pay for protection with Faygo.