Viewing profile — yamarldfst

yamarldfst

HN member

No profile information was provided.

story
Comment #48503099
Fri, Jun 12, 2026, 12:08 PM UTC
comment
Comment #47332953
The framing of "constraints over instructions" at Level 6 is the most underrated point here. In my experience, the reliability jump from telling an LLM "always output valid JSON" v…

Wed, Mar 11, 2026, 8:23 AM UTC
comment
Comment #47332897
what is the meaning of this!??

Wed, Mar 11, 2026, 8:16 AM UTC
comment
Comment #47332890
interested, keep us posted!

Wed, Mar 11, 2026, 8:15 AM UTC
story
Ask HN: Agentic search vs. RAG – what's your production experience?
There's been a clear shift from 2023's you need RAG to 2026's agentic search outperforms RAG. We made the switch at Cosmico when building AI-native applications with Claude Code. A…

Tue, Feb 24, 2026, 8:07 AM UTC
story
Comment #47134239
Tue, Feb 24, 2026, 8:04 AM UTC
story
Comment #47122936
Mon, Feb 23, 2026, 2:39 PM UTC
story
Comment #47122834
Mon, Feb 23, 2026, 2:32 PM UTC
story
Show HN: AgentDX – Open-source linter and LLM benchmark for MCP servers
MCP servers are proliferating fast, but most have vague tool descriptions and incomplete schemas that make LLMs pick the wrong tool or fill parameters incorrectly. AgentDX is a CLI…

Wed, Feb 18, 2026, 4:28 PM UTC