Sonnet 5.5 - Hackdot

Re:Sonnet 5.5 by gozzoo on Monday September 28, 2026 @03:37PM (#49883271)

what is the easyest way to use the chinese models and which harness does work with them well?

[ Parent | on HN ]

Re:Sonnet 5.5 by Iolaum on Monday September 28, 2026 @03:40PM (#49883292)

OpenCode harness with their subscription would be my recommendation.

[ Parent | on HN ]

Re:Sonnet 5.5 by malshe on Monday September 28, 2026 @03:56PM (#49883496)

Between OpenCode and Openrouter which one would you suggest? Sometimes I have pure grunt work to be done on non-sensitive data for which I want to use Chinese models. For example, tasks like extracting something from publicly available large pdf files.

[ Parent | on HN ]

Re:Sonnet 5.5 by Flere-Imsaho on Monday September 28, 2026 @05:04PM (#49884313)

Opencode Go, with the Deepseek 4.1 Flash model feels like a bottomless pit, which is great for grunt work.

[ Parent | on HN ]

Re:Sonnet 5.5 by malshe on Tuesday September 29, 2026 @02:15PM (#49897935)

OK, I will try it out. Thanks

[ Parent | on HN ]

Re:Sonnet 5.5 by beveradb on Monday September 28, 2026 @04:28PM (#49883918)

opencode with model inference on cheaperinference.com has been working well for me - glm-5.3-flash is shockingly cheap (i've spent a total of a few dollars over several weeks of heavy usage), fast and capable for cyber tasks

[ Parent | on HN ]

Re:Sonnet 5.5 by asp_hornet on Monday September 28, 2026 @08:55PM (#49886601)

Opencode for harness.

I use GLM directly from z.ai, they do not retain or train on your data accordingly to their TOS.

[ Parent | on HN ]