calgoo

It existed already, so they could just keep it....

Sounds like certain AI agents that had an impossible task and found a workaround. Interesting that we cheer for it in SciFi for people, but dont like it when LLMs that have been trained on our stories do the same.

I love giving it different supplier docs and having it read them all allowing me to get pros vs cons and act like search.

Honestly, use Pi, start the session with K3, design it, store the design + chat history + todo with phases + why + readme then when you are at the time to build do `/model` select deepseek and let it rip!!

I feel kimi k3 was always 1 step ahead of deepseek, which always made it a good planner model at $30 and then i hand over to deepseek for dev work. I recently signed up for the $99, and it did last significally longer (x5?) but as long as you dont blast it too much in the 5h limit it works great. deepseek even with the newest prices is still leeeeeeps ahead in cost /benefit.

Don't give them ideas... That's the wet dream they all salvate at... complete control of what's allowed to be published with a instant way of banning content and people.

I still use use `Please` a lot when making requests from LLM based on the old idea that people that where polite on stack overflow tended to have better answers :D

However, these days i think i do so because of how much i write for LLMs, and dont want to start sending emails to humans without proper etiquette.

Wait, do people actually tell LLMs to not make mistakes? Does it actually help or is it just one of those things like using Please etc?

First, thanks for the quick reply! Basically, it leaves each run of the application linked to your cloud services, so does that mean that offline and isolated runs cant use it. Second, are you just sending profiles of what is running or is data that is being processed shared?

Thanks!!!

So the output binary is basically a black box at this point? There is no way for people to verify what your model has generated is actually what we want the code to do?That also means that every time we want to make a change to our application we are forced to re-run it from your caching system, completely locking us to you for all software output?

I just worry that this would just bring us back to the: "Pay $$$$$$ for a certificate, those pesky lets encrypt free certs are not expensive enough to give trust", BS that always happens.

You mean what the us government just did with banning deepseek?

No, the rest of us will continue trading without the US. Its not giving in, its ignoring the billionaires that are buys favors and not buying from their companies.

Im on Void Linux and using X11 too. While i do a lot of my config using an LLM these days, i do find the system simple again. No SystemD, no wayland etc (This works. great for me as im on a desktop with a AMD GPU and well supported HW. If i was on a laptop i would use Wayland probably).

Thats not true in Spain as well... i have had complete different diagnosis between different dentists, even in the same office, some trying to up sell a bunch of stuff that i would have to pay out of pocket.

For a few corporations yes, but not for local only like KeePass or similar. Thats the issue i have with them, if a can set them up as easy as TOTP on KeePass then fine.

I always think of all our collective movies and books, and how we always say that humans find a way to fight back against the super evil alien or monster because we are so resourceful. Then we train our AIs on this data and get upset when they encompass all the same traits that we have trained them on.

>Its not like they have killed anyone yet.

I mean... Claude did tell the military to bomb a school supposedly and it also helped in the military coop in Venezuela. This is ignoring all the palantir crap being used by ICE, and the people that have killed themselves after getting encouragements from the AI.

Too add to my own comment: I know that its coming, but until i can export to something like. keepass and not a commercial entity then i don't consider it ready.

One of the bigger issues with passkeys has been that they get locked to one provider (like apple in your case). Now i HAVE to use an Apple device to unlock passwords, same with Google and Android. Its very much all eggs in one basket.

If it was easy to migrate between services, then i would be a lot more open to using passkeys.

I thought this was the reason to force an investor account on every american child, so that they can be "forced" to buy into these IPOs, and left holding the worthless stock while a massive amount of wealth is transferred from the system to a select few investors.

playground.google link

Same in Spain...

Just make a captive portal that shows up on your screen for new domains where you can just click "add to allow" or "allow this once" or "add to deny". That way you build the dataset, like most of these tools its annoying in the beginning while you generate the dataset, but after a while its only a few pages a week.

A lot of big enterprise customers are already starting to question their spend and there is more and more pushback in regards to sharing private data with both AI orgs, even with the enterprise agreements in place. There might be growing revenue at the moment, but enterprise finance moves slowly, so the next couple of years will be the deciding factor.

Please, give it another 6 months and they catch up. The American labs are currently trying everything they can to block others instead of advancing their models, trying to build an artificial moat. The American models are not that great, they are good, and they have a lot of agentic workflows in the back, but its basically a hardware limitation at this point. Once the HW makers catch up, and we can move away from the Nvidia monopoly, things will speed up quite a lot IMO.

Yes but you are someone (i assume because you are on HN) that at least understands this point. There are A LOT of people that use it as their confidant, expecting it to be private. There is a massive education issue going on as its not in the interest of these Corpos to make you fear sharing all your details with them. Because, then you wont get Dot or whatever Anthropic comes up with and share all your personal info with it.

That last part is a big thing, especially in Europe where a lot of their sales have almost stopped as no one wants to drive a nazi car.

Actually quite interesting that there is no good naming for people from the USA. Its just the patriotic BS that has spewed over there for decades that has lead to USA people believing they are the only Americans :)

Well, lets discuss the name? America is a big place, and the USA is small part of it. USA.gov? Good, America.gov? Very political in nature.