axpy906

That’s kind of funny since a Chinese model started the thinking chains being visible in Claude and OA in the first place.

Post should be hire. People are missing the point they traded out data center cost for human cost.

“ That is what drew Gen. William Tecumseh Sherman for one of the Civil War’s seminal campaigns that helped defeat the Confederacy.”

To be clear Sherman burned it to the ground which is why it got renamed Atlanta.

Isn’t that the soul cooking lady from the Podesta files?

Edit: yup looks like it

ZDR in place at API level but need enterprise contract if on a plan. Vendor lock-in and IP drivers.

Yeah, saw Mericari and had some flashing lights go off.

Most Japanese tech is in - well Japanese - companies like Mericari, Woven and Rakuten are exceptions, hence you get a blog post on how to speak English properly.

すぐ死ね Sugu shinu The die quickly game

Have 2.5 in prod. Hope they release 3 lite soon so it will be easier to swap them. Holding my breath as pro pricing is a non starter.

The scariest party is the uniparty.

Based on what Amazon team you are in more than half are born in India. Makes sense they’d be moving operations there.

My eyes.

Ohh. Reply from Shawn. I love your work. As far as I recall, we were not looking for a net of features but specifically a git like API that could manage and version the prompts. Meta data tagging, Jinja2, release labels and easy rollback. Add that up with Rest, Typescripts and Python support and it worked pretty well. Langfuse seemed way better at tracing though.

I haven’t used their product so you’re probably right. I’m biased as an AI engineer because I get contacted to help implement AI in existing platforms. While I admire the pivot the reality is what they have is already quite behind. Anything I make these days is old in about three months… You’d ideally want to start fresh and not have to worry about codebase that is years old.

I don’t know about that. I looked at them a couple of months back for prompt management and they were pretty behind in terms of features. Went with PromptLayer

SaaS company pivots to AI. Gets funding rebranded as AI company. Buys a company that actually knows it.

It’s still early but I question how much of these SaaS companies will continue. I’d rather connect Claude or whatever to do my task than have to learn a new platform let alone login to it.

This great. I want to switch to android but the only thing stopping me is eight years of photos. No more.

“the landing portion of the stage looks like this” Have not seen that ever and had an NES

So Gemini was the most non-deterministic model of them all and now we get this one with temperature at 1 and max thinking. It’s so random that it’s hard to justify putting in my setup right now.

> the internet in 1988

60k computers ( mostly at institutions ) in 20 countries

Probably relates to some of the political controversies surrounding the source NPR here: https://grokipedia.com/page/NPR_controversies

I am both bemused and disappointed that the top comments are all political. Kind of plays into what Billionaires like Bezos would want - the commoners bickering and not united.

I don’t think I ever could do all the 25 so this is fine with me.

Arthur’s classifier will only be as accurate as their retrieval. The approach depends on the candidates to be the correct ones for classification to work.

I don’t get it. Why no American accent?

Suggest adding 2024 to the title

My experience was while it had longer context it didn’t do as well on coding tasks. I use CC after being on Cursor.

Backend engineer here. I have no clue either. I think you’re getting downvoted because it’s easy to search?

> I'll be shocked if anime isn't available on YouTube.

In 2002 it was and I really liked it then.

I am glad I stumbled upon this thread. I’ve not heard positive things in the past about graph dbs. That said, working with legal documents, it makes sense to have both vector and graph search (after candidate refinement) for this domain…

Do the hikes add up?