Muhammad Ramzan

@Sam_Axiom What font is this?

NUMBER SYSTEM — Complete Formula Sheet Series The chapter that builds your entire maths foundation 📖✨ Complete revision notes with formulas, concepts, tricks & examples.

@code Looks like a ripoff from Github Themes.

Your @code just got a fresh look! 🎨 The new default themes, VS Code Light and VS Code Dark, bring a modern, refined design while keeping the familiar usability you love. ⭐ Bonus: these themes automatically match your OS light/dark mode.

@yiliush This will only work if you can optimize the memory usage.

testing something

Every engineer I speak to is worried about the future of their profession. I tell them to join a company that requires them to: - Solve increasingly complex problems that require deep nuance and taste - Build big agentic systems that require specialized AI/ML knowledge - Flex their communication skills as the role of PM/Engineer converge - Maximize their use of coding agents & AI tools in their workflows - Breadth of projects that improve taste and dot connection over time p.s. this is the expectation of every engineer we hire at @tenex_labs. apply and stay relevant in a post-ai world.

@stevekrouse Let's build one.

I have a customer with a ton of PDFs they want an LLM on top of, but we're hitting context window limits Is there a high-level API that lets me upload a bunch of PDFs, and then provides a "tool" that I can give to an LLM?

@Thedevil_Of_HK @Amank1412 Nope. Loving it.

@LightifyCodes @Amank1412 Is it stable ? Have you encountered any issues with it ?

Is there a way to make VS Code look like this?

@kai_brokering @claudeai Wow. One man's trash is another man's treasure.

completely forgot i have $30k worth of @claudeai credits that expires in 3 weeks wtf am i supposed to do with all this😭

@shivambhadani_ Checkout this great playlist by @sriniously youtube.com/playlist?list=…

@lydiahallie I thought you were asking for @vercel

Love seeing all the Claude Code agent team demos on my feed ❤️ Have you tried them yet? Curious to hear what you think!

New Engineering blog: We tasked Opus 4.6 using agent teams to build a C compiler. Then we (mostly) walked away. Two weeks later, it worked on the Linux kernel. Here's what it taught us about the future of autonomous software development. Read more: anthropic.com/engineering/bu…

@ivanfioravanti @ivanfioravanti I think a very interesting comparison would be to use the same prompt and environment but do everything with claude code. This would reveal how coding agents can influence a model's performance.

Royal Rumble opencode edition! 🔥 GLM 4.7 vs MiniMax 2.1 using opencode and respective coding plans to build a website on sports cars, prompt and issues below. Final websites at end of video. 1/3

@infiniteloop44 @SumitM_X @grok Can you shed some more light on this?

That pattern is called JWT pass-through (or token forwarding). > Is it secure? Technically yes, architecturally risky. It works, but it couples every service to user auth and doesn’t scale well. Why: > You’re leaking a user-facing token deep into internal services > Token expiry, scope mismatch, and over-privileged access become common > Any compromised service can impersonate the user downstream > It works for small systems, but at scale it’s an anti-pattern. Better approach: > Terminate OAuth at the edge > Use internal tokens or service identity for service-to-service calls > Propagate user context as claims, not raw JWTs Rule of thumb: > User tokens stop at the boundary. > Use internal service tokens or token exchange for downstream calls.

A user logs in and gets a JWT. That JWT is passed from Service A -> Service B -> Service C to complete one request. What is this pattern called ? Is it secure ?

@Zai_org if a task is very complex or it is deemed that GLM might not have seen this then: -> Opus 4.5 generates a detailed plan with all the historical context and explanations. The plan goes straight to GLM and it can do it's magic.

@Zai_org @Zai_org has really enabled developers with less monetary resources to build remarkable things. That's how I've built my setup. -> GLM 4.7 is the main driver. All the tasks of upper intermediate nature go directly to GLM and it works like a charm

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! 🎉 👉z.ai/subscribe?utm_…

@Zai_org I have high hopes that in near future I might not need the Opus step and GLM can be my primary and only driver.

@amonyx @grok 2799

🚨 PICK A NUMBER BETWEEN 1–5000 🧠 @grok will select the WINNER tomorrow at 9 PM EST 💎 #XRP

@dopabees mramazan1@yahoo.com

We're hiring Software Engineer Interns at Lemon AI. $60/hr. Fully remote. Competitive equity. Like this post and drop your email below. We'll reach out.

@michelleefang Hi @michelleefang. I'm building autonomous cloud tools.

if you're vibe coding or building over the holidays, i want to gift one of you a 6 month subscription of claude pro to support <3 just drop a comment below. merry christmas!

@CodeByNZ @ApidogHQ

any alternative to postman ?