Misbachul Munir

I'm a curious guy, want to know just about everything. I like to learn about web development, latest science and do a lot of adventures on Linux land.

[Misbachul Munir @m_goku]

@k2sbhai Are the free credit available for everyone? How to claim it ?

[Misbachul Munir @m_goku]

@boltdotnew @EricSimons Forge

[Misbachul Munir @m_goku]

@OrcaRouter I use deepseek-v4-flash-free. Information from the model card, context window is 1M. But, i got the error very early during the session when the context window is less than 50k

[Misbachul Munir @m_goku]

@OrcaRouter i keep getting this error 400: This prompt is longer than the free tier allows for a single request.

Where can i find any information about prompt length cap for free tier ?

[Misbachul Munir @m_goku]

@jahooma All country?

[Misbachul Munir @m_goku]

@blueemi99 Been using it for several days. The first day it feels amazing. But, the experience degraded, and now I feel the model is nothing special. I don't know, maybe too many user reduce it's power.

[Misbachul Munir @m_goku]

Been enjoying free Deepseek v4 Flash 0731 via Freebuff. Great harness, free model. The catch ? you will see ads, and for Deepseek case, your data may be used for training. Otherwise, it is great platform.

https://t.co/gEOpxw7dQa

[Misbachul Munir @m_goku]

Freebuff, the fre coding agent. Obviously there are going to be ads in the interface, but everything else work amazing. Some country has limited model selection and session limit, refreal will increase the session limit

https://t.co/gEOpxw7dQa

[Misbachul Munir @m_goku]

Hi, @CommandCodeAI , I think you need to properly render the table content.

[Misbachul Munir @m_goku]

@MrAhmadAwais Wow. Are you serious ?

Deepseek v4 flash is already very good in Command code. Gona try Stepfun flash

[Misbachul Munir @m_goku]

Hi @CommandCodeAI , should I check the taste.md files into git or should I ignore it ? what is the best practice here ?

[Misbachul Munir @m_goku]

@vipulgupta2048 @CommandCodeAI I mean, somekind of how gemini-cli or opencode show the model thinking process like in this

[Misbachul Munir @m_goku]

@MrAhmadAwais @CommandCodeAI @vercel Been using it for several days. The only problem i had is that Command Code does not show the model COT, and i can't find any way to enable it.

[RadixArk @radixark]

We've heard the community's feedback. Our intent was to make sure the credits reached the people who supported SGLang along the way, and we couldn't be here without you. We're updating the offer to better reflect that.

RadixArk's platform is open for beta, and we're offering $200 in compute credits to get you started
→ Sign up at https://t.co/MVDvcvkFGX and repost this so we can get you set up.
→ Limited spots, first come first serve. Open through May 13, 2026 (AoE).
→ Credits will be granted after we verify the repost.
(If you already reposted our earlier announcement, that counts too; no need to do it again.)

And if SGLang has been useful in your work, consider giving it a star on GitHub. It's a small gesture that means a lot to the people maintaining it. We're in this together, and we're grateful to be building it with you 🧡

[Misbachul Munir @m_goku]

Been using Deepseek v4 pro in @CommandCodeAI for the last 2 days. Its good, but once in a while, it failed tool call: Invalid input for tool "grep".

[Misbachul Munir @m_goku]

@MrAhmadAwais I'm ready

[Misbachul Munir @m_goku]

@NVIDIAAIDev @Kimi_Moonshot I tried kimi k2.5 here and from the https://t.co/4JfudGZnvC website, with the same prompt, the result is far different. I ask it to compare itself with another models. The output here is completely outdated while the output from the official kimi web is excellent. How come ?

[Z.ai @Zai_org]

We’re officially public. (HKEX: 02513)

To everyone who has supported GLM, built with it, tested it, or simply followed along. Thank you.❤️
This moment belongs to our community as much as it belongs to us.

To celebrate, we’re opening a 48-hour community challenge.❤️‍🔥❤️‍🔥❤️‍🔥

48 hours. A few ways to join!
💬 Comment challenge
Every 12 hours, we’ll select the top 25 comments by likes. Each will receive $50 in credits.

🔁 Repost challenge
Every 24 hours, we’ll select the top 13 reposts by likes. Each will receive $200 in credits.

⭐ Editor’s picks
Some of the most interesting ideas don’t always get the most likes. We’ll be reading closely and highlighting thoughtful, original developer posts.

If your post is selected, Lou @louszbd will reach out personally with an exclusive developer gift pack.🎁

We’ll wrap up in 48 hours. All rewards will be sent within 72 hours after the challenge ends.

Let’s celebrate! 🎉
👉https://t.co/n5FbqerBd1