News for hackers. Stuff that matters.
Re:Why is GPT-5.4 obsessed with Goblins? by ghostlyInc on Tuesday March 10, 2026 @07:29AM (#47321814)
LLMs tend to pick up recurring metaphors from training data and reinforcement tuning.

Words like “goblin”, “gremlin”, “yak shaving”, etc. are common in engineering culture to describe hidden bugs or messy systems. If those appear often in the training corpus or get positively reinforced during alignment tuning, the model may overuse them as narrative shortcuts.

It's basically a mild style artifact of the training distribution, not something intentionally programmed.

Re:Why is GPT-5.4 obsessed with Goblins? by d--b on Tuesday March 10, 2026 @09:16AM (#47322872)
They seem a lot more common in OP's conversations than in any regular engineering conversation though. Like I've been an engineer for 20 years. I don't remember the phrase used in my work context, ever.
Re:Why is GPT-5.4 obsessed with Goblins? by ghostlyInc on Tuesday March 10, 2026 @11:32AM (#47324653)
That's fair. It probably depends a lot on which corners of engineering culture the training data comes from. In some communities (older Unix culture, Hacker News, ops/debugging discussions) terms like “gremlins”, “yak shaving”, etc. pop up more often as humorous shorthand for messy problems.

But you're right that in day-to-day professional environments they aren't used nearly as much. So it might also just be the model over-generalizing a small stylistic pattern it saw frequently in certain parts of the corpus.