JP

Just built a community platform for the @TanStack + @convex hackathon! 🚀 ✅ Video calls (@Cloudflare RealtimeKit) TanStack Start framework & Convex backend. It was a wild ride. Thanks for the opportunity @tannerlinsley @jamwt @waynesutton youtu.be/jYz6RCr2RFw

@viditchess @GrowthX_Club does this include a bullet game with the winners?

I’m judging a @GrowthX_Club Hermes agent buildathon this weekend! Excited to meet & interact with the builders and tech folks of Mumbai. It will be interesting to see & evaluate products people will ship that day!

@framer Computer Vision Platform Landing Page

✨ Free credit time? To celebrate the launch of GPT 5.6 Sol, Terra, and Luna, we’re giving 10,000 extra credits to the first 100 followers who reply with what they’re going to build. Make sure to follow us and reply, and we’ll DM you the credits.

Introducing RazorSense - a design language for humans in the AI era, alive in every state and expressive in every interaction. Go experience it now ↓ razorpay.com/razorsense/ #Razorpaydesign #Razorpay #Productdesign #UIdesign

@theodormarcu stop giving it away for free.

If you liked the recent OSS model releases (Kimi K2.7/GLM 5.2), you’re going to really like SWE-1.7 The team shipped major improvements over SWE-1.6, especially on UX and long-horizon tasks. SWE-1.7 feels meaningfully closer to the frontier / premium model tier than ever before, and you can use it for free in Devin Desktop/Cloud/CLI

@ayushagarwal @supermemory @dodopayments is this virtual or in peson event?

we have joined hands with @supermemory for localhost:6767 as the official payments partner. build it with supermemory. sell it with @dodopayments. winners get sponsored credits. july 9-13. come build with us.

Our free dictation announcement went viral — and yes, it’s real. For anyone who didn’t watch the full video, here’s the simple version: Willow Frontier Mini is now free for unlimited dictation. No caveats. Willow Frontier Pro is our more advanced model: faster, more accurate, and available on paid plans alongside unlimited Scribe, our AI writing assistant. Why are we doing this? No, you are not becoming the product. You are not becoming the data. Willow is on a mission to save a trillion hours of productivity by killing the keyboard. Voice is the most natural interface we have. Speaking to your computer should be free, fast, and accurate, not limited by bad dictation tools or locked behind a paywall.

We're extending access to Claude Fable 5 on all paid plans through July 12.

@ClaudeDevs i always get advisor not available `fable 5` even if i have set it.

A few patterns we frequently use with Fable 5: Use Fable 5 as an "advisor." An executor (Sonnet 5) calls Fable 5 for guidance. Most tokens are billed at the lower executor rate.

@Razorpay @AnthropicAI @peakxvpartners when mumbai?

Calling all AI builders to Bangalore 👋 We're teaming up with @AnthropicAI and @peakxvpartners for “India Builds with Claude”, an evening dedicated to people shipping real AI products. Showcase & Learn 🏆 $10K in Claude API credits for the Top 3 demos 🎙️ 1:1 with @harshilmathur for the overall winner Apply here → luma.com/8v8l5x5g #BuildWithClaude #AIBuilders

@theo rough edges means more resets 😂

Apparently I'm allowed to talk about GPT-5.6 now? It's a damn good model. Not quite as "smart" as Fable, but it is incredibly capable. Fixed all the problems I had with GPT-5.5. It is incredibly determined. Will run for a day without even using a /goal. It understands subagents incredibly well and is great at orchestrating. It's super pleasant in use cases like OpenClaw and Hermes Agent. It knows iOS dev incredibly well. It has rough edges too, but FAR fewer than 5.5 did. For many things, gpt-5.6-sol will become my obvious default. I will share a lot more soon 🫡

@kammysliwiec @nestframework 🤌

It's here. Our new @nestframework website is live. ✨ Our first major redesign in 9 years. It's still us, just sharper - a cleaner, faster, and more modern experience built for the next chapter. Take a look and let us know what you think! nestjs.com

Built NEON SPRAWL — a fully animated cyberpunk gaming landing page in @usewonder Wonder's chat agent handled the whole build — glitch animations, neon palette, monospace HUD typography, the works. What you design is what you ship. app.wonder.so/jay-p/files/01… #WonderChallenge @usewonder @contra

@benln Yes

Rebooting my X group chat for people building projects on Sundays. One rule: you can only post on Sundays. Reply if you want in.

Meet Nimo 🏮 — the keeper of the little lantern. Built entirely in @recraftai Studio for the #recraftchallenge on @contra - one little character carried across a whole bedtime world: plush, nightlight, storybook, and every small comfort in between. Same Nimo, every time. 💛 recraft.ai/project/dd9893… #recraftchallenge #recraftai #mascotdesign #characterdesign #brandmascot #AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️

@zaidmukaddam @cognition @DevinAI congrats, was there any 1-1 talk with the @cognition team before joining the program?

exciting update: i got into the @cognition devin ambassador program! time to go all in on @DevinAI and share it with y'all while helping it grow! also, i'll be doing a lot of events and possible workshops soon in Mumbai! really excited to grow this community in Mumbai! more soon.

GLM 5.2 max by @Zai_org combined with @DevinAI harness - for Code reviews is too good. Thanks @cognition for making enterprise grade software available for all.

@dakshgup No gotcha's? i mean usually org train on data, if they are giving it for free.

introducing greptile's free tier. we've made a lot of improvements over the past few months to greptile, and we want to share those with more developers. you can now get 50 reviews per month as a solo developer for free

Built Ledgerline for #H0Hackathon: usage-based billing for B2B SaaS on Amazon Aurora DSQL. So I made it provable: 250 concurrent writes w/ duplicate keys → 0 double-counts. DSQL's strong consistency does the work. ledgerline-tawny.vercel.app Created for the H0 Hackathon. #AWS #AuroraDSQL #Vercel @vercel @v0 @awscloud @devpost

🌳 Meet Grove — a living 3D world where 25 independent Gemma 4 agents perceive, think & act in parallel. Every thought bubble is a real LLM output. Powered by @Cerebras (~5,600 tok/s) + @googlegemma Gemma 4. Built for the Gemma 4 Hackathon. github.com/ik-labs/grove

@encoredotdev @warpdotdev

What's your terminal of choice?