Thread

1. onomojo · 1786044657 · focus · HN ↗

   Any benchmark showing Opus 5 as the best just loses credibility for me. Anyone who's actually used Opus 5 daily knows what I'm talking about.

   1. visarga · 1786045080 · focus · HN ↗

      Sent to solve one task, came back with half of it solved and 2 more problems.

      1. vunderba · 1786055134 · focus · HN ↗

         What really enrages me is the amount of effort it puts into justifying weaseling out of work. (THAT'S MY JOB!)

         It will do everything it can to defer or push it off, to the point where I’ve had to add multiple imperative directives to the AGENTS file telling it, in no uncertain terms, not to defer tasks under any circumstances.

         1. cyanydeez · 1786059353 · focus · HN ↗

            sounds like someone needs a local llm.

            1. vunderba · 1786059988 · focus · HN ↗

               Oh I do. Headless 128GB RAM machine serving llama.cpp with a number of local models that I use on a daily basis.

               • Qwen3-VL picks up new images in a NAS, auto captions and adds the text descriptions as a hidden EXIF layer into the image, which is used for fast search and organization in conjunction with a Qdrant vector database.

               • Gemma3:27b is used for personal translation work (mostly English and Chinese).

               • Some small 8b models (like llama3.1) for sentiment analysis on text.

               But haven't really tried using local LLMs in conjunction with agentic harnesses yet.

               1. cyanydeez · 1786060995 · focus · HN ↗

                  recommend opencode w/qwen 35B or 27B with MTP.

                  My secret sauce is to use LLAMAcpp's reasoning-budget and reasoning-message that trigger cut off to overthinking with a message that says to either us subagents or compress the context. opencode's dynamic context pruning plugin can get you pretty far into the stratosphere.

                  1. vunderba · 1786061310 · focus · HN ↗

                     > My secret sauce is to use LLAMAcpp's reasoning-budget and reasoning-message that trigger cut off to overthinking with a message that says to either us subagents or compress the context

                     Thanks for the tip - I like this a lot. I remember having to do a lot of tweaking to curtail Qwen QwQ-32b when it would go down an endless psychotic recursive reasoning loops as part of its "chain of reasoning."

Unofficial Hacker News client; not affiliated with Y Combinator.