Joined 7 months ago
I am going to develop the next version TermOnHost, which will let you connect to all kinds of hosts (Mac, Windows, Linux, or any Linux embedded system) And your hosts can connect to each other.
Is there anybody using it ?
Not easy to trust the choosed skill is work: - No input example - No output example
It's hard to play and trust the "skill".
But you know, engineers bullshit each other all the time too. The difference is we have a way to verify it - logical chains. You have to build an argument that holds up before anayone buys in it.
So I though, can I make AI build its own logical chain ? Let it pass its own logic check before telling me the result.
That's how I created my own "think" skill. It's based on Meta's CoT paper: https://arxiv.org/abs/2501.04682
It roughly works like this: 1. FRAME - Challenge the question itself, hidden assumptions.
2. GROUND - Map what you know, what you need, what's missing.
3. ASSOCIATE - Launch multiple independent agents in parallel to generate hypotheses, avoid anchoring bias.
4. VERIFY - Break each hypothesis into atomic claims, verify each independently
5. CHAIN - Build a logical chain from survivors
6. PROVE and LOOP - Walk backwards from conclusion to premises, seearch for evidence, repair if broken
7. DELIVER - Start with "I was wrong if ...."
It helps me a lot. Whenever I need to check if Claude Opus 4.6 is bullshitting me. I just say "/think verify the above reasoning is correct" or "/think verify the above fix is correct and complete."
Would that make you reconsider coding remotely from your phone ?
For example, I'v implemented "Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought" into a skill and the AI becomes able to "think".
The correct rate becomes higher but the only drawback is consuming token very much.
- vim: NERDTree, Gblame
- zsh
- tig: best way to browse git history in terminal
- claud code
