Arne Strickmann

One app. Every agent.

Open-weight models, and GLM-5.2 in particular, are capable of handling complex coding tasks. Run GLM-5.2, Kimi-K2.7, or any other model in Emdash with your preferred harness.

@qui_rins @slobkebap @emdashsh unf. not:/

@slobkebap @arnestrickmann you in town to showcase @emdashsh ?

looking for one more cracked founder for tomorrow's Claude for Founders event in Berlin to showcase their flow, anyone we NEED to have?

@AdhyaayK @emdashsh Hey, yes -you can use Emdash with your local gh CLI, so you don’t need to create an account.

@emdashsh Can yall add local gh cli support bc I don’t want to have to connect emdash to my org, but still be able to use it properly

What's new in Emdash v1.1.38: - New chat UI powered by ACP - GPT-5.6 Sol, Muse Spark 11, and Grok 4.5 - Notion integration - Oh My Pi and Zero CLI support - Storage management - Drag terminals into task tabs - Voice mode support on macOS - Task archive shortcut: ⇧⌘E Plus lots of fixes and improvements.

At 11k employees, our AI costs are going up. Which model & harness should we use to lower cost but also retain great quality? We didn't want to blindly trust public benchmarks. So we ran a comprehensive evaluation on our tasks, code base, infra. It's been produced by more than 3,000 software engineers, spans 3 hyperscalar clouds and many languages and tasks. The results are surprising. We find that for the SAME mdoel, the choice of harness can significantly save costs (~2x). We also find that GLM 5.2 performs extremely well. We run Omnigent in front of these and can easily multiplex different harnesses and models for different tasks. Check it out: databricks.com/blog/benchmark…

Yes

@BensHasThoughts 😎

@arnestrickmann I did typos before it was cool

Symptom of the LLM era: intentionally added typos in posts and articlöes

Damn

@marty_kausas Give Emdash (emdash.ai) a try - unified interface for every harness and model:)

i'm so sick of using claude code in a terminal i'm not coding. who has made a great app that i can use with any model?

New home: emdash.ai

@emdashsh Emdash has quietly become my daily driver — parallel Claude Code agents in worktrees just works.

@f14wn 🦵

sunday is lagday

@marcklingen +1

chat/cowork/code switchers are all not great LM Studio has figured this out a long time ago (and then scrapped it again lol, old screenshot) Pattern only makes sense as chat > cowork (> code) is mostly purely incremental in capabilities and complexity

@kvnkld 👌

What a model week

Muse Spark 1.1 is now available in Emdash with OpenCode.

@sriramk Give @emdashsh a try; one experience across every agent and model.

We've got something for you

GPT-5.6 Sol is now live in Emdash. Compare it against Fable, GLM-5.2, Kimi-K2.7, or any other model.