TIL that @Docker now has 1-click deployment for dockerized LLM's 🚀! Been a big fan of @lmstudio and it's super easy auto-switch model capabilities - We'll see how this stands up to it

Open source supabase-devops-toolkit:.

After way too much frustration and broken restores, I finally caved and built my own @Supabase backup/restore tool. One command to clone prod → local (with smart role handling) → done. And yes, it’s open source 👇🏻

I do have to hand it to @OpenAI - nobody comes even close to their conversational tech. High hopes for @grok and @GeminiApp but in terms of noise cancellation, interruptions, latency, consistency - chatgpt is doing circles around them.

It's customer experiences like this that really make a difference in gaining / retaining customers. Huge shout out to @expo - I wish there were more companies out there with this mentality!

Just had @getsentry detect a app crash, review the crash, provide a solution for the crash, and deploy a PR. All without having to lift a finger 👆. What a wild world we live in. Nice work Sentry!.

OpenAI’s attempt to humanize their realtime ChatGPT conversations with #gpt5 have turned their functional Ember character into that of a male flight attendant personality 🤦🏼‍♂️.

How can I get an agent to respond to cursor agent in order to have it continue from a stop loop? I find many prompts are “please continue” as the result is 1/20th baked.

GPT-5 is capable but lazy AF. Needs some tuning.

Is there any pipeline that exists where you can go from design system component (figma) to generated front-end code (storybook, react components) that actually look and analyze your components and custom icons properly? (Thinking offset casual game UI style not shadcn everything).

Large software teams are dead. AI integration is mandatory and @DannPetty - counter to your previous post, audience is everything. Trusted following and network will surpass any talent in art and development now.

Imagine if Apple blew everyone away at WWDC this year with a on-device llm that was competitive to gemeni 2.5/sonnet 4. So far on-device quantizes models haven’t been able to get anywhere near cloud capable llms.

This is wild. Close your eyes and you can actually feel something from their responses. Not perfect but hell it's come a long way is such a short time! Kudos @elevenlabsio.

Gemini 2.5 pro and Claude 4 are all you need. Opus, o3 and more expensive models aren’t worth the cost for development. Convince me otherwise.

Google IO is a great example of how fast tech is moving and how cut-throat AI is. Every day people’s products are turned into small ‘features’ by the big players, essentially replacing them overnight. What are AI ideas that you think are niche enough this wont happen?.

Wowza! Figma just killed Illustrator, Framer, Aura and more. Well played!. #figmaconfig2025.

Has anyone else been experiencing outages with @cursor_ai over the last few days. Seems to just sit there hanging at generating. Restarts, etc don't seem to solve the issue.

Does anything beat Gemini 2.5 Pro when it comes to coding? Gemini 2.5 Pro far surpasses Sonnet 3.7 – It feels pretty AGI'ish, even has the laziness to make it believable. Just wondering if o3/o4-mini actually surpass it when it comes to code.

There are a lot of tools out there to create PRD’s, and templates for cursor rules but they are generic and don’t think they actually scale that well from product to product. In my streams, we will start by setting up a project one at a time!.

Gonna start live streaming how to setup projects using @cursor_ai in the most effective manner. Setup PRD’s, flows, cursor rules, MCP’s so that when you leverage the llm they can stay on track and execute production ready code! . What are some projects you want to see built?.