chillfox

Cool story, but I only got about 1/3 down the page before the AI-speak got too much and I gave up.

I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago when it started being rate limite/captcha'd frequently.

My main reason for liking it is that it just gives me results without any ads or special summary/snippet/QA/etc... boxes.

I really wouldn't mind paying API pricing for search, I think it would end up at less than $10/year, but I haven't seen a good self-hosted search interface that allows plugging in api keys.

For comparison, audiobookshelf idles at 89MB, emby at 178MB and navidrome at 29MB for me.

I think everyone has different definitions of what they consider heavy. I tend to think anything using over 30MB when idle is a bit much and anything over 300MB is something that really needs to earn it's spot.

GLM 5.2 was the first open model that I was happy to use as my main. It's a fantastic model. 5.3 cost a lot more per task, was slower and didn't get that much better results for me, so I tried 5.3 Flash for a bit, it was ok, but didn't feel as magical as 5.2 and I have now landed on DeepSeek 4.1 Flash as my main.

Who in their right mind would buy a case that’s past the statute of limitations?

Because the big labs are incredibly untrustworthy. Their leaders are publicly lying constantly.

I don't think so.

If they actually believed in it, then they would stop pushing the frontier of capability and instead focus on alignment, safety, and better tools for controlling/debugging AI. Then they would actually share their findings and tools.

They don't do this. Instead of reducing the competitive pressure and helping the industry to build safer more aligned models they are doing the exact opposite.

Because those are not the only examples.

There’s the case of the agent that hacked a gym when asked to book a class. That was just a normal user asking an agent to do a normal thing.

Isn’t there some Chinese site hosting all the models?

I hated that part of SO so much. Almost every time I got a SO result on google it was exactly the issue I had and without fail the question would be closed as a duplicate pointing to something that was different enough to be completely useless to me.

You can structure it so that it becomes accidental.

  1. Ensure security barriers are weak or honor based.
  2. Put individual researchers under a lot of pressure.
  3. If you get caught, blame the weak barriers, or the individual researcher.

Basically setup the incentive structure to incentivize researchers sticking their mittens in the private cookie jar while putting the cookie jar in a dark unmonitored/unsecured room with a sign on the door saying please don't enter.

I never actually managed to use fable successfully even once on a pretty standard mvc/microservice app.. It would always find the endpoint permission checks and revert to opus 4.8.

I also had glm 5.3 flash fix an issue that opus 5 could not solve. glm took 4 times as long and a sub-agent tried to cheat (sleep; echo ...), but in the end it actually solved the issue. opus 5 never figured it out.

I think the safeguards might be cooking the anthropic models.

OpenCode Go is becoming less of a good deal by the month. I pretty much only use it for mimo 2.5 pro now, and everything else is either ollama or openrouter.

Seeing the price, I am probably just going to keep using GLM-5.2 until 5.3 gets cheaper.

The average game dev cycle is about 7 years these days, so expect to wait some more years before you see llms used much in games.