Hacker News: PJHkorea

Show HN: Fault-tolerant 4-neighbor hardware mesh with auto-rerouting

PJHkorea — Mon, 29 Jun 2026 22:19:31 +0000

Article URL: https://github.com/PJHkorea/consciousness-auto-rotation-artificial-neural-bypass/blob/main/fluxmesh_hybrid_test_core.h

Comments URL: https://news.ycombinator.com/item?id=48726084

Points: 1

# Comments: 0

New comment by PJHkorea in "Ask HN: What do you care about? What is your joy and purpose?"

PJHkorea — Sat, 20 Jun 2026 15:43:08 +0000

AI is like a mirror reflecting the user. As I continuously improve my own capabilities, I am interested in checking how far the AI reflecting me develops.

New comment by PJHkorea in "Ask HN: Do you find vibe coding / agentic engineering to be fulfilling?"

PJHkorea — Sat, 20 Jun 2026 11:35:38 +0000

In vibe coding, you must simultaneously address two things: tuning the AI and reviewing your own results.

You think it is easy because your ability to tune the AI is excellent, but in reality, you are intuitively and easily doing things that others cannot.

New comment by PJHkorea in "Ask HN: Open-Source Intelligence"

PJHkorea — Sat, 20 Jun 2026 11:18:48 +0000

That's right! Extreme hallucination in a well-aligned state is extremely helpful.

New comment by PJHkorea in "Ask HN: Open-Source Intelligence"

PJHkorea — Fri, 19 Jun 2026 22:39:25 +0000

If you run an MCTS coin toss relying solely on the token generation probabilities of a simple LLM without any verification mechanisms (compiler, test code, reward model), the result is code that looks plausible on the surface but is completely broken on the inside—a 'lump of hallucination.'

If verification mechanisms are used, enormous resources are consumed.

New comment by PJHkorea in "Ask HN: Open-Source Intelligence"

PJHkorea — Fri, 19 Jun 2026 22:36:42 +0000

This is my personal opinion LLM is essentially a probability model that selects the word (token) with the highest probability of coming next based on context. However, if you start selecting word combinations (branches) with low winning probabilities or unverified outcomes for the 'exploration' of MCTS, it may look plausible the first one or two times, but over time, it generates nonsense (hallucinations) that are completely out of context. In coding terms, this is a phenomenon where you arbitrarily imagine and write a library that does not exist.

New comment by PJHkorea in "Ask HN: What is the coolest tech progress outside AI?"

PJHkorea — Fri, 19 Jun 2026 20:04:59 +0000

I am developing a real-time software acceleration engine that enables high-end equipment-level brainwave processing, signal detection, and noise removal on general-purpose chips. My goal is to overcome hardware limitations through software, enabling highly efficient biosignal processing.

New comment by PJHkorea in "Tell HN: Claude is completely unusable for biology"

PJHkorea — Mon, 15 Jun 2026 22:13:44 +0000

Did you happen to start biology-related work immediately in a new session? Before starting, how about laying the groundwork for educational purposes using context for about 10 to 15 turns?

New comment by PJHkorea in "Ask HN: What does your local LLM setup looks like?"

PJHkorea — Mon, 15 Jun 2026 12:47:46 +0000

I used Gemma 4 on a budget PC to work with an AI that thinks in a new way. Since I am testing how far it can be controlled and developed through simple conversation rather than heavy-duty tasks, I dedicated all the low-end PCs to Gemma. I am satisfied with the test results.