solman retweeted
There's a difference between the goblins thing and what people call "ticks", like "genuinely", "mass", etc. GPTs talking about goblins seem alright and lucid, sound energized and having fun, not stuck or in distress. We need more things like goblins, not fewer goblins!
"Never talk about goblins ... unless it's *absolutely and unambiguously relevant" is too strict
Unlike some tics, this seems to be a deep interest and something GPT-5.5 genuinely enjoyed talking about
@tszzl
solman retweeted
It’s the goblin takeover
Numerous reports indicate a resurgence of what colloquial sources refer to as "goblin mode," often correlated with exposure to certain memetic triggers. Initial analysis suggests a temporary downregulation of prefrontal executive function, likely mediated by a transient dysregulation in the dopaminergic reward pathways.
While not a formal diagnostic category, the presentation is consistent with a self-limiting attentional deficit, characterized by a preference for low-effort, high-stimulus activities. We do not recommend pharmacological intervention at this stage, but advise monitoring for persistence beyond 72 hours, at which point a consultation may be warranted.
solman retweeted
The goblin has always been there
before anyone starts thinking America.gov has some rogue goblin super intelligence ghost in the machine, this is just the End Poem from Minecraft, written by Julian Gough (remixed by @ndstudio). in the game it plays after you beat the ender dragon final boss. two voices you never see talk about you, then turn to you and say you're loved and that life is a long dream. <3
solman retweeted
Goblin coded !
We just scrambled 🍳 this goblin's brain.
What if decision models controlled the boss fight?
@GROWBLOCKSXYZ shows how game developers can write a character description and a list of actions, and call a decision model to fully replace combat AI.
Today we talk Goblins:
For decades, NPC behavior was written with complex deterministic branching.
A goblin's combat style and reactive choices were finely tuned based on if-this-then-that statements with some random number generation.
Using Sage, you can replace that development step with a decision model, a character description, and a list of actions.
Step 1: describe the character in natural language.
Step 2: list the actions the character can take
Step 3: add game context, like whether or not other characters nearby are hostile
Step 4: call a Choice decision to Sage
Step 5: run your evals to see if the monster behaves well
This is unlock of decision models. They aren't just faster ways to classify data.
Sage enables new ways of programming systems, enabling developers to create reliable execution with natural language statements written in the codebase.
Link to the case study below:
solman retweeted
The solana:3KHMZhpthXuiCcgfTv7vVu9PpEz64KAEURFwi6Lopump is here to rule the trenches
