adamsmark

Was intrigued then saw the obvious LLM speak. If someone doesn't bother to de-LLM that means they never read the output in the first place.

Boo this man! Boo him!

Hey, letting you know I'm stealing your quote about CREAM. It'so absurd.

"They" is so much easier.

I always felt like saying if "he or she" took too much time and was unnecessary.

"They" will replace Him and Her! It might even be you! (If I ever refer to you in 3rd person)

Why not use Linear/Plane/Paperclip?

E ink is at 60hz now. Look up Bigme B7 (it's wild!)

A lot of optimism and I think they got it right. We're now arming even more and lamenting the loss of all this expensive cold war stuff that was getting rolled out (Virginia class subs?).

We had an unprecedented run of prosperity and American dominance in so many sectors.

The 3D visualizations have always made it starkly apparent the difference in quality between quantizations and thinking.

The pelican meme is so much better than benchmaxxed stuff. Unfortunately we are likely now in pelicanmaxxing territory.

There are stupid TVs but they're more expensive since they don't have an ad subsidy.

I'm doing what you are - just don't connect it and you can enjoy ridiculously low prices on TVs.

The US used to see itself as a policeman. It is now kinda going gangster.

You can't police a multipolar world - you can when you're the sole superpower in a unipolar word where "policing" can be a euphemism.

I think there is now a general or at least generational attitude shift about world policeman type stuff vs smash, grab and bully in America.

Utah Kentucky North Carolina

Every single time I'm hoping to see Washington State and I'm always let down.

Sort by "Best Sellers" always on Amazon. "Featured" is driven by ads. Also? Firefox with Ublock Origin blocks ads (but it's an endless cat and mouse game).

Any sources on the $1.5M effects of yoga on goats study? Google nor ChatGPT could find anything.

Anyone have any thoughts on how Herdr already addresses what they're building?

This might be a good alternative to Terminal. I can use a cheap e reader like the Boox Go 7 to display whatever.

My guess is they are getting folks used to the idea of:

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.

I worked for OnePlus a few years ago, managing its Amazon account.

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.

Something that has worked surprisingly well for me is journaling via voice recording on my phone. It's been so effective that I've mapped it to my phone's physical shortcut button.

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.

The Chinese would love this.

Groq was the preview of the broadband era of LLMs for me. I remember asking a question on the demo site and the answer text showed up near instantly. Far faster than I could read. This was ~1 year ago and pre-acquisition.

It wouldn't continue in any real form. Maybe cholesterol conscious and devout buddhists will still try to adhere, but beyond that I don't see what the point would be.

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.

Echoing that. 99 Bottles really was an institution. It had the feel of a proper local pub: warm, a little scruffy, and full of character. The walls were covered with bottle caps from all kinds of beer brands — probably more than 99, honestly.

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.

Burn some "incense" to help you get in the zone. Bless the machine spirit!

I want to use local LLMs, and in fact I have enough VRAM (12GB) and RAM (96GB) to do it but I gave up because it was pretty buggy with the Gemma 4 26B (A4B?) Q4 models. It also meant I had to give up local voice transcription because I needed all my VRAM dedicated to the LLM.

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.

Heck no. I had fun though.

Write caveman summary too. Fast read.

But you can turn off brain. Try make self idiot. Save brain energy for important. Smarty speaks in idiot. When smarty speak like that is consistent. Idiot understand fast.

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.

I use my Openclaw setup to record notes I don't ever want to remember the details of. Here are some examples:

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.

Local isn't viable yet on an economic basis, API costs are so low that you're better off taking advantage of the bonanza. As local models become more performant, so too will the ability of providers via Openrouter be able to offer them cheaper than your likely payoff period for a $4K Mac Studio 128GB. e.g Gemma 4 31B is impressive, but it costs practically nothing via Openrouter. Given that there are a ton of providers for open models, I doubt there's any subsidy going on because the providers are faceless and interchangeable.

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.

The accuracy is much lower though.

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

Whoop! Whoop!

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