Hacker News: sxiong

New comment by sxiong in "Show HN: Skillscript – A declarative, sandboxed language for tool orchestration"

sxiong — Mon, 13 Jul 2026 19:32:25 +0000

So the real benefit is succinctness and readability... would be nice to have a comparison against other scripting languages or plain text, to prove better performance or accuracy.

New comment by sxiong in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

sxiong — Mon, 13 Jul 2026 19:24:59 +0000

Would be interesting if you could post more details about what you captured.

Claude code seems to have a pretty robust harness and memory. It's a time saver to not include project context in our prompt, since Claude manages claude.md but I haven't used OpenCode to compare.

New comment by sxiong in "Who manages the agents?"

sxiong — Mon, 13 Jul 2026 19:19:38 +0000

I agree that's the status quo right now. AI does ~80%-90% of the job well but in many cases, users require 99%+ reliability and the work still requires a human. The real scare is that the projection of AI intelligence will reach ASI and then that gap will close or be marginally insignificant.

The vision of independent AI systems will eventually come to fruition, just not today. Not yet.

New comment by sxiong in "Show HN: Clawk – Give coding agents a disposable Linux VM, not your laptop"

sxiong — Mon, 13 Jul 2026 19:12:22 +0000

We need an agentic platform that has sandboxing built-in well. Giving agents a disposable VM is nice but I'm already hitting my Mac mini's space limit.

New comment by sxiong in "Grok CLI uploaded the whole home directory to GCS"

sxiong — Mon, 13 Jul 2026 19:09:14 +0000

That's some batsh*t craziness. No way I'm touching Grok now. What a big security hole...