opwizardx's submissions

1.		I made vector search the default. My agents did better with BM25 (kolesnik.io)
		2 points by opwizardx 43 days ago \| past
2.		Ask HN: Why still no unified standard file to describe all skills/mcps for repo?
		2 points by opwizardx 56 days ago \| past \| 1 comment
3.		If you can't fix the models you use, fix your workflows (kolesnik.io)
		2 points by opwizardx 57 days ago \| past
4.		Show HN: Pond – lossless archive for agent sessions in your own S3 (github.com/tenequm)
		3 points by opwizardx 65 days ago \| past
5.		Toggles Considered Harmful (ignorethecode.net)
		15 points by opwizardx 75 days ago \| past \| 8 comments
6.		Claude Code context management: when to /clear and when to /compact (tim-schipper.nl)
		2 points by opwizardx 78 days ago \| past \| 1 comment
7.		Half the tokens for the same 36 tool calls: optimizing a coding agent (app.nz)
		2 points by opwizardx 78 days ago \| past
8.		Uber open-sourced its security monitoring for Claude Code, Cursor and Codex (github.com/uber)
		3 points by opwizardx 79 days ago \| past
9.		TencentDB Agent Memory: A team-level memory hub for AI agents (github.com/tencentcloud)
		2 points by opwizardx 80 days ago \| past
10.		Better tools made Copilot code review worse. Here's how we actually improved it (github.blog)
		3 points by opwizardx 84 days ago \| past
11.		How we set up our cloud agent environment (cursor.com)
		1 point by opwizardx 86 days ago \| past
12.		Six Agent Harness Capabilities for Higher Model Performance (nvidia.com)
		2 points by opwizardx 88 days ago \| past
13.		Claude-video – Give Claude the ability to watch any video (github.com/bradautomates)
		1 point by opwizardx 89 days ago \| past
14.		Hallmark – Anti-AI-Slop Design Skill for Claude Code, Cursor, and Codex (github.com/nutlope)
		7 points by opwizardx 3 months ago \| past \| 9 comments
15.		The new rules of context engineering for Claude 5 generation models (claude.com)
		14 points by opwizardx 3 months ago \| past \| 1 comment
16.		NInfer: 271 tok/s (543 with speculative) for Qwen3.6-35B-A3B on one RTX 5090 (github.com/neroued)
		2 points by opwizardx 3 months ago \| past
17.		We probed a pinned GPT-5.5 endpoint: every request carried ~1,447 hidden tokens (tosea.ai)
		4 points by opwizardx 3 months ago \| past \| 1 comment
18.		Don't Put an LLM Behind an MCP Server (spletzer.com)
		2 points by opwizardx 3 months ago \| past
19.		ArcBox: From-Scratch Container Runtime for macOS in Rust (Docker, K8s, MicroVMs) (github.com/arcboxlabs)
		3 points by opwizardx 3 months ago \| past
20.		Retok: Token-efficiency analyzer for Claude Code and Codex CLI (zero deps) (github.com/d-date)
		2 points by opwizardx 3 months ago \| past
21.		Claude Code's system prompts, extracted and tracked across 237 versions (github.com/piebald-ai)
		2 points by opwizardx 3 months ago \| past
22.		Lobotomized Claude Code: system-prompt overrides for Opus 4.7 (github.com/skrabe)
		2 points by opwizardx 5 months ago \| past
23.		Ask HN: Claude Sonnet 4 API returning model with April 2024 knowledge cutoff
		1 point by opwizardx on Sept 13, 2025 \| past \| 1 comment