Ankur Patel

@Aditya_181105 Yes indeed

Bro disappeared like he never existed.

@nexonjexaris @Venkydotdev Really? Kimi better than Opus and fable?

@Venkydotdev Kimi now : 😏😈

anthropic two months back now

@prayag_sonar @ClaudeDevs Is kimi better than glm5.2? (For coding purposes)

@ClaudeDevs Kimi forced Claude to continue fable 5 and keep limits high

We're also keeping Claude Code weekly limits 50% higher, now through August 19, for all Pro, Max, Team, and seat-based Enterprise users.

@techyygarry @ClaudeDevs That's true. Once a month we should have such option included in subscription. 😂

@ClaudeDevs For one month, give us this option. We will change the world.

@humzaakhalid Nice way to prompt detailed plan.

Anthropic just caved. Fable 5 is now included in the max subscriptions forever. They won't say why. Everyone knows why. ChatGPT 5.6 sol shipped at a fraction of the price, and it's good. When the cheaper model stops being the worst, "premium" stops being a strategy. But here's what nobody is saying: Fable 5 is still the token-for-token king. 5.6 sol is smart like a rabid hyena. Huge power, terrible aim. Fable is smart like a surgeon. It stays on the thing you asked for. That only matters if you know how to drive it. A million people just got unlimited access to the most focused model on the market. Most will type "make me a video," get slop, and call it overrated. The model isn't the moat anymore. The prompt is. How I route work now: Fable 5 → planning and complex tasks 5.6 sol medium → simple, fast, cheap 5.6 sol ultra → long-running goals Kimi K3 → great, but not cheap enough to leave Claude Code For Fable, I stopped writing prompts. I write 11 blocks in order: 1. Task: what the video must do 2. Context: what Fable needs to know 3. Reference: what good looks like 4. Effort: how precise to be 5. Act: the main scene 6. Scope: what must not change 7. Delegate: split into 3 beats 8. Evidence: proof it worked 9. Memory: style rules to reuse 10. Checkpoint: quality gate 11. Report: what gets delivered Skip Scope → extra hands and random text. Skip Checkpoint → you ship the broken take. Skip Memory → every video looks like a different brand. When labs compete, we win. Full high-res cheat sheet, free, below.

@marceguerra @MahimSky_ @X Let's connect

@MahimSky_ @X Same

Hey @X algorithm 👋 I’m looking to #connect with people interested in: - SaaS - Frontend - Backend - Full-stack - DevOps - App Development - AI / ML - Data Science - LeetCode & DSA - Freelancing - Building in public If that’s you, let’s connect👤

@kushmergedeck Hey @kushmergedeck, we are into almost all you have listed - SaaS, AI, Automation, Web apps, and Tech products. Checkout Keyntech.com

Hey founders! Looking to connect with people building in: • SaaS • AI • Automation • Web apps • Tech products • Marketing Drop what you're working on 👇

@araseb_ horizontal scaling a good option here.

Interviewer: Your API is getting 15,000 requests per second. Server is choking. Users are complaining. You have 15 minutes to fix it. What do you do?

@ziwenxu_ @ClaudeDevs Same here. - Any idea why?

@ClaudeDevs Everyone is on GPT 5.6 I didn’t even see this in my feed 😆

We've reset 5-hour and weekly rate limits for all users.

@thsottiaux @ClaudeDevs Haha - Indeed.

@ClaudeDevs I smell fear

Dry Run mode = see the exact replacement count for every URL before Replacely writes a single byte to your DB. No surprises. No “wait, what changed?” Slack messages at 6pm on a Friday. 👀 🔌 wordpress.org/plugins/replac… 💻 github.com/ankur2194/Repl… #WordPress #WPDev #WebDev #NoCode

Blind sitewide find/replace on a production WP database is how agencies lose a weekend. Replacely only touches the URLs you list, the exact text you specify. Nothing else moves. Dry-run first, then ship. 🎯 github.com/ankur2194/Repl… #WordPress #WPDev #Elementor #BuildInPublic

@DeRonin_ is GLM actually reliable for agent loops though? that's the one swap i'm genuinely skeptical about.

My entire AI stack is now Chinese 🇨🇳 87% cheaper. same revenue swaps by task: 1. reasoning / backend brain Opus 4.8 → Kimi K2.7 benchmark gap: ~8% · price: ~11x cheaper 2. code generation GPT-5.5 → Qwen 3.7 Max benchmark gap: ~18% · price: ~7x cheaper 3. agent loops + tool calling Sonnet 4.7 → GLM 5.2 benchmark gap: ~3% · price: ~5x cheaper on input 4. cheap volume / bulk processing GPT-5.5 mini → MiMo V2.5 benchmark gap: ~6% · price: ~12x cheaper 5. image generation GPT-Image-2 → Wan 2.5 benchmark gap: ~5% · price: ~8x cheaper 6. video generation Sora 2 → Kling 3.0 benchmark gap: roughly equal · price: ~6x cheaper [ result after 30 days: ] operating costs dropped 87%, output quality dropped 4% on average, revenue unchanged the most important that these models will be not banned in a month and i can run them locally nobody will steal my data and i can learn them as i need full article drops tomorrow with: > exact routing logic per task type > the 2 cases where I still pay for American > the migration playbook anyone can copy in a weekend VERY IMPORTANT to get migrated now, while it's not too late

This free UI library is crazy 🤯 ui.tailus.io is one of the best UI libraries in 2024. It's free 💯 and open source.

Fun lil detail: dark mode favicon <link href="favicon.png" rel="icon" media="(prefers-color-scheme: light)"> <link href="favicon-dark.png" rel="icon" media="(prefers-color-scheme: dark)">

@goldenboypierre @slimphp I've created an issue. github.com/slimphp/Slim-S… Please reply there if anyone can help. Thanks!

🔥 New Angular Material Release 🚀 📦 9.0.0-rc.0 🏗 RELEASE CANDIDATE 🏷️ #angular #material #components #cdk #release #changelog #releasebutler 🔗 #900-rc0-2019-10-31" target="_blank" rel="nofollow noopener">github.com/angular/materi…

New Password Confirmation Flow for Logged In Users in Laravel 6.2 laravel-news.com/new-password-c… by @paulredmond