theredbeard
Joined 8 months ago
Karma
79
Submissions
25
Member since
Feb 9
Recent submissions
Comment · 7 months ago
We haven’t been inching closer to users writing a half-decent ticket in decades though.
Comment · 7 months ago
This is because for some reason all agentic systems think that slapping cron on it is enough, but that completely ignores decades of knowledge about prospective memory. Take a look at https://theredbeard.io/blog/the-missing-memory-type/ for a write-up on exactly that.
Comment · 7 months ago
What in the ChatGPT is this?
Comment · 7 months ago
I’m getting pretty decent at spotting LLM text. This doesn’t contain the obvious tells at least.
Comment · 7 months ago
It’s a self fulfilling prophecy. They’re extremely expensive so they must be good so they must be worth it. And because at that level measurement is extremely subjective it’s mainly about the vibes.
Like everything it’s just marketing.
Comment · 7 months ago
I’m sorry but no attempt was made here. It contains all the red flags in the first few paragraphs.
Comment · 7 months ago
A vibe? It’s completely obvious AI slop with no attempt to make it legible. They didn’t even prompt out the emdashes. For such a cool finding this is extremely disappointing.
Comment · 8 months ago
It's a fair question. I've had problems with Gemini 3 due to rate limiting, and I've been working on this for a while now. I'm planning Gemini 3 for a follow up.
Comment · 8 months ago
It’s not groundbreaking in a technological sense. The codebase is actually a bit of a monstrosity. But it removed guardrails that were artificially put on these LLMs which suddenly gave it an entire new dimension and the timing was right.