gandreani

It's such a little thing but while reading the opinion I see that the court (Kagan in this case?) makes a factual claim it provides SOURCES.

https://www.supremecourt.gov/opinions/25pdf/25-112_0am4.pdf

"Modern cell phones, we observed a dozen years ago, are “such a pervasive and insistent part of daily life that the proverbial visitor from Mars might conclude they were an important feature of human anatomy.” Riley v. California, 573 U. S. 373, 385 (2014). Since then, the percentage of Americans who own smartphones has only increased. To- day, more than nine in ten Americans own a smartphone. See W. Bishop, Pew Research Center, Mobile Fact Sheet (Nov. 20, 2025) (91%); compare A. Smith, Pew Research Center, Smartphone Ownership—2013 Update (June 5, 2013) (56%)."

It's not clear in the code how you're batching the writes. Could the performance improvement be mostly explained by batches?

Using gpt-5.4-mini in off-peak hours already feels like super-speed to me. That's probably no more than 100-150 tk/s. I can't imagine 750!

I've always eyed Cerebras but never had a use for it that would justify paying for the API directly. Although now that I think about it, trying out the API would probably cost less than a subscription for a month...

Easily the most interesting part of this announcement is buried in the second to last paragraph:

"We're also launching GPT‑5.6 Sol on Cerebras at up to 750 tokens per second in July, bringing frontier intelligence to customers at unprecedented speed. Access will initially be limited to select customers as we expand capacity."

750 tokens/s on a frontier model is going to be extremely interesting. I doubt this new version is anything but a version bump in terms of capabilities but if we can start getting these answers back faster, they end up being more useful.

Just off the top of my head, I can think of the tedious task of finding certain functionality within a codebase. I usually can't beat an AI agent harness at this task today. If the AI model is 3x faster I have less of chance.

I believe you! I wasn't implying anything about your project. I just can't quite shake the feeling.

Man I have the strangest Deja Vu with this comment. I swear it's like the third time I read this??

I use both the openai subscription and the opencode go subscription. I use the go subscription for my personal work and the openai subscription for my consulting work.

The differences between the models are minimal, but I usually stick with gpt-5.4-mini, gpt-5.4, mimo-pro-2.5, deepseek-v4-pro. These latter ones have way more usage than even using 5.4-mini so I tend to use them in personal projects for that reason.

My harness is https://github.com/can1357/oh-my-pi. I trust it...enough. It updates very frequently so as a safe guard I run it sandboxed with https://github.com/containers/bubblewrap so it can only access the project folder and some whitelisted config files

"Death of Silicon Valley" in this case is such a funny perspective. Like, how twisted is the US's view of the market that they think "Competition? Oh no. Sound the alarms."

I also have this problem!

It's the only model where an explicit instruction at the end of my message is sometimes ignored. This doesn't happen with any of the gpts, kimis, glms, qwen, etc. Just a deepseek problem.

Hope it improves!

I use it through my opencode go subscription and it's exactly how you described. Very pragmatic and not too ambitious. It's similar to Kimi 2.5/6 in that regard.

I like it!

Have you tried DeepSeek V4 Flash? It's very competent and extremely cheap.

I think Gemma 4 is also a good example of a capable small model.

I mention these not only because they're cheap but because they can run on consumer devices. The "every year bigger and more capable SOTA model" trend is mirrored by "the every year smaller and more capable open source model" trend.

Are you using Mimo 2.5 pro?

Writing tests is also something AI agents excel at. At least they excel at converting plain english instructions into exact tests.

I haven't hand written tests in a while and it was something that I always bemoaned. Not anymore!

Azure suspended your account as well?

But...AWS is a platform too, no? Seems like you're in the same category of risk you just moved to a more well-known name. Granted, Amazon is the most reliable even if they have their own quirks.

Drilling in the basement seems like a pain to remove the dirt you dig up. Saving yourself a couple of feet cannot be worth the access troubles

Oops I mixed up my tabs. My bad

There's a video!

I can't get over the fact of how suspicious he looks while doing it. And doesn't even cover his face. Crazyness

https://x.com/porqueTTarg/status/2047652413306277970 https://xcancel.com/porqueTTarg/status/2047652413306277970

And backups. Sqlite makes it easier but no backup process is easy. You always have to backup and restore at least once to have the confidence to rely on it.

It's another (big) point towards paying someone else to host it.

Do you like Netdata? I'm looking into it. I'm curious if you use all the features or just a few.

I really like this post! I think it's the clearest explanation I've seen of the different characteristics of utf-8 strings

I don't know about McD's exactly, but food in general is very cheap in Japan compared to the U.S.

Source: I watch a lot of behind the scenes restaurant videos on YouTube and I'm always shocked at the prices. Most dishes are cheaper than if I were to go to the grocery store and cook it myself...

I had the opposite happen to me. I made the same assumption when my GPU broke (it was 2-3 months old). I thought I'll save time and spend some more money to have it repaired in a local shop instead of sending it back to the manufacturer.

Turns out it was a fatal irreparable failure. A capacitor overheated and left a small crater on the surface. Because I took it to the shop, the warranty sticker was void. Had to buy a whole new GPU :(

Wow props to that sales rep. Not many would pass on the opportunity to sell something more expensive. I'm assuming they make some sort of (paltry) commission

This is funny. This change actually pushes me into using a competitor more (https://www.kimi.com). I was trying out this provider with oh-my-pi (https://github.com/can1357/oh-my-pi) and was lamenting that it didn't have web search implemented using kimi.

Well a kind contributor just added that feature specifically because of this ban(https://github.com/can1357/oh-my-pi/pull/110).

I'm happy as a clam now. Yay for competition!

The aliases we're tripping me up! I almost understand it now. Not sure what the @lp is doing

This is very cool. I have no idea how this one work. I'm guessing most of the magic is in the box shadow?

https://codepen.io/yuanchuan/pen/OJRqGvz

What did you use for the graphs on the site? They look nice!

What are you using now and what are you looking for in your new platform?

Maybe somewhere in the original comment it would have been fair to mention you can barely see the house in the original photo. This is actually a hilarious complaint