Cline

We’ve been impressed with GLM-5.2 and so are introducing a $9.99/month subscription to give you 2-5x discounted access to it and other open weight models like DeepSeek, Kimi, MiniMax, Mimo, Qwen. Use it on Cline CLI & IDE with $1.99 special promo if sign up via: npm i -g cline

TIL of SlopCodeBench, a benchmark for how coding agents slowly turn codebases into slop. instead of single shot tasks like swe-bench, the agent gets several tasks one after another so eg bad architectural decisions early on lead to worse results for the later tasks. compared to 473 human written python repos, agent code is: - 2.3x more verbose (redundant) - 2x more eroded - degrades 5-7x faster per change than humans do across their git history we are now anti slop engineers

glm fast mode is my new daily driver for 9/10 tasks where i need to iterate fast. fast, cheap, and imo best bang for buck this is why you shouldn't lock into single model agents, you leave alpha on table given the wide array of options out now.

which model wins the vibe check?

Try in Cline with model id: openai/gpt-5.6-sol To install Cline in your CLI: npm i -g cline Available as an extension for VS Code and JetBrains as well! (Free, open source, bring your own API key and use any model) github.com/cline/cline

GPT-5.6 sets a new Terminal-Bench record at 91.9%. Priced the same as GPT 5.5 at $5/$30 per million tokens. With Fable getting pulled from Claude subscriptions and moving to API cost (~2x as expensive at $10/$50), we are glad to see @OpenAI's commitment to accessibility.

Muse Spark 1.1 just launched and it's their most capable coding agent model yet. On Terminal-Bench 2.1 it scores 80.0%, in the same cluster as Opus 4.8 (82.7%) and GPT 5.5 (83.4%). Use it in Cline with the Meta API!

Try in Cline with model id: x-ai/grok-latest To install Cline in your CLI: npm i -g cline Available as an extension for VS Code and JetBrains as well! (Free, open source, bring your own API key and use any model) github.com/cline/cline

xAI has just released Grok 4.5, beating Opus 4.8 on Terminal-Bench. Notably, Grok 4.5 is served at fast speeds w/ 2x greater token efficiency than other top models, while being priced ~5x cheaper than GPT. Meaning it delivers the highest intelligence per unit of time and cost.

Inspired by Anthropic's JSpace paper, we @cline used @modal to host a public demo so anyone can watch a Jacobian-lens view of what a small language model is representing across layers/tokens. Try it:

To install Cline in your CLI: npm i -g cline Available as an extension for VS Code and JetBrains as well! (Free, open source, bring your own API key and use any model) github.com/cline/cline

Tencent Hy3 represents a breakthrough in open source intelligence. It's topping benchmarks at only 295b params / 21b active, making it a frontier level model you can run local on your own hardware. Free in Cline so you can feel it for yourself. Use model id: tencent/hy3:free

we hired a famous balloon artist (shout out Agnes So!) to make an 8 foot tall @Cline balloon for @aiDotEngineer it ended up being $5000, totally worth it right?

@das_rdsm @OrganicGPT would love to learn more about whats causing this - is there any details you can give? what os you're using or what you did to fix it the first time?

@OrganicGPT @cline Lucky you, Ive got the annual one. I will try asking for a refund. :(

@Cline CLI is so bad I'm surprised they let it ship like this. I've told them about this but they haven't fixed it yet. Should I cancel my ClinePass subscription?

@dennypradipta_ @bitsbyritik Yes we just posted an update, did something stop working for you?

@cline @bitsbyritik Do you happen to pushed an update today? Because I swear to god this thing works since 1st of July.

Trying to test out the ClinePass for some agentic workflows, but it's not showing up as a provider in the @cline CLI only getting the Usage-Billing option. Has anyone figured out how to connect it? Am I missing a step here? 🛠️

@VangelisMedina Yep! step-3.7-flash and deepseek-v4-flash

@cline Just subbed Cline Pass. There are more free models?

New free model in Cline! Laguna M.1 by Poolside. Speedy 225B total parameter model with 256k context, built for agentic coding and long-horizon work. Use the model id: poolside/laguna-m.1:free

@joelszw @HuangRenee3 Fixed in the latest v3.0.35! Please update with: npm i -g cline@latest Apologies for the trouble 🙏 (and thank you for all the details, it was very helpful!)

@HuangRenee3 @cline Your welcome

We’ve been impressed with GLM-5.2 and so are introducing a $9.99/month subscription to give you 2-5x discounted access to it and other open weight models like DeepSeek, Kimi, MiniMax, Mimo, Qwen. Use it on Cline CLI & IDE with $1.99 special promo if sign up via: npm i -g cline

@dennypradipta_ @bitsbyritik Hi folks, are you using min-release-age in your .npmrc? You might be on an older version of the CLI.

@bitsbyritik @cline After using it for a few days I can’t seem to connect to the ClinePass too. Have you solved it yet?

To install Cline in your CLI: npm i -g cline Available as an extension for VS Code and JetBrains as well! (Free, open source, bring your own API key and use any model) github.com/cline/cline