

I had it exposed for maybe ten years (mostly so that users could manage their accounts), nothing bass happened, but i have shut down that server about a year before the ai security disaster, so ymmv


I had it exposed for maybe ten years (mostly so that users could manage their accounts), nothing bass happened, but i have shut down that server about a year before the ai security disaster, so ymmv


Nice! Many of new features, someone put lots of love into this
That is quite cool but just to make sure, have you heard of Gemini the protocol?
It won’t help you browse documentation but grows out of the same observation that html is not sustainable


Thank you, this is a lot of new names for me and a great starting point for research. This field changes so fast


Deepseek on a single GPU? How? Q2 or something like colibri?


Qwen/Gemma 30B that you can run locally on a regular higher end pc can write some simple software making many mistakes and correcting itself all the time. It can intelligently search in code bases quite well.
GLM that you can self host if you sell your house and buy GPUs for that can one-shot most regular software tasks, like adding some functionality, and can handle larger tasks like “write me an app that looks like x and does y” while making mistakes and correcting itself which takes more time. It can do security and privacy reviews of code bases too.
Claude Opus can one-shot a mobile app on an uncommon platform and the code will usually be well designed and work straight away.
That’s my experience, anyway.


I’m all for self hosting but glm can be used with hosted providers and it costs peanuts. You can also pay z.ai directly, but of course one day they may turn off the ability to reverse engineer stuff.


So i can play directly to my kodi box hooked to speakers? I must try that


What’s the use case? I heard of people giving their agents lightning wallets for x401 but i have never heard of usdc for that use (and can’t really imagine what any of these is used for with an agent)


You think OP is fake?


Aren’t you going to get used to it after a few days, like to everything else in life?


Something that would make good use of a 128GB spark. GPT-OSS-120b is good but shows its age
Jami is an old project and every time I revisit it there’s some strong smell of things not being right one way or the other. Even before it became p2p and was the SIP client sflphone it was doing funky stuff such as notifying about non existent calls.
Which is to bad because they have good ideas but terrible execution