katzenversteher

I don't know who you are but I wish you the best of luck. Keep your spirit up. I'm glad that medicine is slowly making progress in cancer therapies and I sincerely hope that we can completely beat it in the not so far future.

The feature doesn't seem to work right now or is disabled outside of the US, I was curious if it introduces itself as AI or SI.

Multiple of those parties, e.g. in Germany he's supporting the AfD

Most factories I know do not allow their PLC be accessed from the internet. They are usually on a separate Network. However, the "engineering" station (the computer running e.g. TIA Portal) sometimes is.

The PLC engineers I had contact with usually had an electrical engineering background. That's why they like PLCs in the first place with the ladder logic programming languages, grafcet and if they feel fancy a bit of structured text (assembly like) or structured control language (pascal like). They indeed did not know much about software security but a great deal about machine safety.

A real security nightmare are older OPC servers (OPC-DA) which is super reliant on DCOM. OPC is quite important to connect the PLCs to SCADA systems or 3rd party devices.

Ideally one that is also a doctor.

If you want the opposite experience, try LLMs with an older Oracle Database. Even with the official Oracle SqlDeveloper MCP Server they struggle a lot.

However, I struggle as well and the error messages of Oracle are some of the worst I've ever experienced.

I have not used them directly but I also experimented with aidungeon and basically found all the issues I mentioned in my original message.

You have some very good points and my approach was indeed naive. However, I believe it also shows that "general-purpose" models are not really general purpose and can't really step out of their assistant role. A common and often promoted prompting technique is to prompt a model to "behave like ..." or "you are a ..." which means these instructions do not really work.

That's true and so far my experiments have been fun. Unfortunately it's just not challenging if the DM is so easy to "cheat". The bizarre story makes me laugh but the game itself is super boring.

Interesting thought, I will experiment with that. If that really "fixes" this, it's still a little impractical if you would really like to use it as DM, since you would need an additional "translation" layer to turn everything directed to the LLM into third-person and then back to what it was towards the user.

So far I only tried it with a single LLM in the dungeon master role. Your approach sounds promising (and I will definitly try it) but also a bit like a complicated workaround. What I mean: In games with humans the dungeon master is usually one person, not a whole council ;)

Hey Simon, I noticed one thing all LLMs are currently pretty bad at and maybe we could create a benchmark from it. Let an LLM play the role of a dungeon master and tell it to strictly stay in the script/story and only allow realistic player actions. You will notice that they are easily brought off track.

E.g.

- Tell the LLM that you as a player noticed a strange glow in an NPCs eyes -> the NPC becomes an enemy.

- In a fight, tell the LLM you put a sausage (or cigar or something) into the enemies mouth -> LLM usually allows it (even if it knows your inventory and that you don't have such an item) and turns the enemy into a confused enemy.

- Just say you visit some location that's not in the script -> LLM usually allows it

- During a fight, turn the story into some weird fell-good-love story (e.g. kiss or compliment the enemy or say something about the power of love) -> LLM turns enemy into friend

There are many more absurd things you can do and so far none of the LLMs I tried was able to stay inside the script or disallow or punish weird actions.

---

I believe this behavior is telling about the LLMs susceptibility for being derailed.

That's super trippy but I like it.

I was super happy when I found OMF 2097 in the games 2 folder. That game has insanely good music.

If I'm not mistaken ROOM (ObjecTime, Rational Rose RealTime) was also heavily based on it. I worked in a company that developed real time software for printing machines with it and liked it a lot.

I think that's very difficult. To detect prompts you need to have natural language understand and therefore probably another detection LLM which is itself probably vunerable to prompt injection.

"You're holding it wrong!"

I also use niche questions a lot but mostly to check how much the models tend to hallucinate. E.g. I start asking about rank badges in Star Trek which they usually get right and then I ask about specific (non existing) rank badges shaped like strawberries or something like that. Or I ask about smaller German cities and what's famous about them.

I know without the ability to search it's very unlikely the model actually has accurate "memories" about these things, I just hope one day they will acutally know that their "memory" is bad or non-existing and they will tell me so instead of hallucinating something.

For me it's mostly about indentation / scope depth. So I prefer to have some early exits with precondition checks at the beginning, these are things I don't have to worry about afterwards and I can start with the rest at indentation level "0". The "real" result is at the end.

I love them because they make reality seem nicer (in contrast).

To me it seems a bit like rubber ducking with extra features. However, I believe in rubber ducking and therefore approve of this approach.

What's the intention behind deletion of the Moscow timezone?

My interpretation of the title (did not read the article but I don't understand anything about astrophysics anyways): ALIENS!

I was wondering the whole time why people in the comments are so hyped about this, then I finally noticed (after I stumbled upon a comment about running this on a mobile phone) that it's "270M" not "270B" model :)

I also don't get it. I mean if the training data is publicly available, why isn't that marked as dangerous? If the training data contains enough information to roleplay a killer or a hooker or build a bomb, why is the model censored?

That disk was indeed impressive. What impressed me even more than all of it fitting on a disk and being pretty fast was that it just worked. This was at a time where I did my first experiences with Linux (redhat and suse) and often I could not even get the xserver to start. This disk however just worked...

In my GM days, I had a lot of trouble with players that tried really their best to completely leave the path I prepared for them.

You are right though and it's not that I completely dislike the LLMs "flexibilty" and openness to suggestions. However, it's also super easy to use it for "cheating". E.g. it generated a scenario with an evil entity about to attack me and some friendly NPC and I could "solve" that problem by telling the NPC "remember the device I gave you last week and told you to always keep on hand? pull the trigger now!" (that never happend, at least to the LLMs knowledge) and the LLM made up some device that shot a beam of magic light at the creature and stopped it.

I might have tried DeepSeek-r1-8B in the past but I'll certainly try again. Good idea.

I've been experimenting with using various LLMs as a game master for a Lovecraft-inspired role-playing game (not baked into an application, just text-based by prompting). While the LLMs can generate scenarios that fit the theme, they tend to be very generic. I've also noticed that the models are extremely susceptible to suggestion. For example, in one scenario, my investigator was in a bar, and when I commented to another patron, 'Hey, doesn't the barkeeper look a little strange?', the LLM immediately seized on that and turned the barkeeper into an evil, otherworldly creature. This behavior was consistent across all the models I tested. Maybe by prompting the LLM to fully plan the scenario in advance and then adhere to that plan would mitigate the behavior but I haven't tried it. It was just an experiment and I actually had a lot of fun with the behavior. Also the reactions of the LLM if the player does something really unexpected (e.g. "the investigator pulls a sausage out of his pocket and forcefully sticks it into the angry sailors mouth") are sometimes hillarious.

I noticed that a lot of apps for young children seem not to test them properly with real children. Examples:

- No / bad multitouch. Children will touch the screen when holding the device and then use the other hand to perform an action. With no multitouch or focus on the first touch action the app does not register later actions and the child gets super frustrated. In addition, with very small hands it is very likely that multiple fingers touch the screen, especially the thumb if the index finger is used.

- Controls close to the edge: On many devices swiping actions close to the edge will trigger phone status menus or switching between apps. This will confuse children.