Viewing profile — theredbeard
theredbeard
HN member- Joined
- Mon, Feb 09, 2026, 8:42 AM UTC
- HN karma
- 79
- Public activity
- 25 items
- HN profile
- View on Hacker News ↗
About theredbeard
No profile information was provided.
Recent public activity
-
comment
Comment #47539769
We haven’t been inching closer to users writing a half-decent ticket in decades though.
-
comment
Comment #47539757
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…
-
comment
Comment #47532737
What in the ChatGPT is this?
-
comment
Comment #47521866
I’m getting pretty decent at spotting LLM text. This doesn’t contain the obvious tells at least.
-
comment
Comment #47339353
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 mainl…
-
comment
Comment #47339316
I’m sorry but no attempt was made here. It contains all the red flags in the first few paragraphs.
-
comment
Comment #47339297
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.
- story
- story
- story
- story
-
comment
Comment #47136895
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.
- story
- story
-
comment
Comment #47038271
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…
-
comment
Comment #47001059
I built this because I was curious what Claude sends to the API, how subagents get work delegated and what contexts look like. Interesting to see how small part of the context the …
- story
- story
-
comment
Comment #46948677
I built this because I was curious what Claude sends to the API, how subagents get work delegated and how contexts look like. Interesting to see how small part of the context the u…
- story
-
comment
Comment #46947243
No worries, the italics did heavy lifting.
-
comment
Comment #46947221
Gitlab.com is the obvious rec.
-
comment
Comment #46944738
What could go wrong?!
-
comment
Comment #46944699
Skipping the investigation phase to jump straight to solutions has killed projects for decades. Requirements docs nobody reads, analysis nobody does, straight to coding because tha…
-
comment
Comment #46943923
OSS was already brutal for new contributors before AI. You'd spend hours on a good-faith PR and get ignored for months, or get torn apart in review because you didn't know the unwr…