Hacker News: collinwilkins

New comment by collinwilkins in "Expensively Quadratic: The LLM Agent Cost Curve"

collinwilkins — Mon, 16 Feb 2026 16:59:28 +0000

what i've learned running multi-agent workflows... >use the expensive models for planning/design and the cheaper models for implementation >stick with small/tightly scoped requests >clear the context window often and let the AGENTS.md files control the basics

New comment by collinwilkins in "Qwen3.5: Towards Native Multimodal Agents"

collinwilkins — Mon, 16 Feb 2026 16:54:50 +0000

at this point it seems every new model scores within a few points of each other on SWE-bench. the actual differentiator is how well it handles multi-step tool use without losing the plot halfway through and how well it works with an existing stack