It’s always interesting to see how much people trust sending such personal information to some service on the Internet, expecting privacy.

I’m not sure I’d even want my own self-hosted LLMs to have something like a personal diary. Sending all that to an AI company would never even cross my mind.

I understand that most people aren’t the tech-oriented types who get into self-hosting and running their own LLMs, but people have had diaries for centuries before LLMs existed.

Care to elaborate? (Or point to where one can learn more about this?)

I have not. Is that game only about torturing the characters, or is that more of a side quest?

🤔 I don’t think it’s quite the same as video games. Video games usually involve some challenge, goal, risk of losing, etc.

There are only a few games that I play though, so I might not be “qualified” to say for sure, but a torture simulator with no purpose outside of torture doesn’t seem like much of a game.

To spend this amount of time and effort building the necessary software environment for “torturing” LLMs is creepy. Like, imagine an adult who builds a bunch of crazy contraptions to physically “torture” some dolls or something. It harms no one, but it’s creepy.

My Hermes instance periodically checks the overall open-weight LLM landscape, and it recently recommended trying Ornith 1.5 35B-A3B.

I haven’t tried it yet, but on paper, it sounds like it has some potential.

🤔 what happens if/when we reach ASI? Do we just call it Super-Duper Intelligence?

I hope they make a MoE version. I get like 50 tokens/sec with Qwen3.6-35B-A3B, but can’t rely on it quite as much as Qwen3.8-27B.

Yep, I’ve been using that same model pretty heavily too, running on ExLlamaV3. It’s very impressive for such a little model!

It’s definitely better than American open-weight models. The gap between American flagship models and Chinese open-weight models is closing quickly though.

With the token prices of Chinese models, I seldom reach for American models anymore.

I can’t even imagine opening up to an LLM, emotionally, or even having a casual conversation with one. Also, other people can read those conversations. How are people comfortable with that?

🤔 Interesting. I never even considered what happens if excess energy is produced

Some (but not all) hybrids are worth looking into, if within budget.

🤔 I’ve never even thought about researching the people who built any vehicle I’ve ever purchased. Where do you start?

How?

(No need to go into too much detail as I’m not in the UK; I’m just curious)

Lol yep.

Though lately I just give the URL to an AI to read and call out red flags. Sometimes there’s an email address buried in the legalese to opt out of data sharing (and the LLM can draft an email to copy-paste). Though, at that point, I’ve usually lost too much trust in the service and find alternatives.

All while selling your personal data because you agreed to that when it was buried in that giant EULA/Privacy policy/etc. that you didn’t read