corbanb 🐻

👨🏼‍💻 👾 Product and Engineering Leader 🧠 ENTP-A. Building. Coding. Designing. Golfing. Dad.

[Molly Ploofkins @Mollyploofkins]

This is weird.

[corbanb 🐻 @corbanb]

@danshipper @every So the moral of the story.

Plan with Opus 4.7

Code with GPT 5.5

[Min Choi @minchoi]

Did Apple just kill every iOS vibe coding app?

Apple just dropped Xcode 26.3 with agentic coding.

Claude Code + Codex are now built into Xcode.

And with MCP support.

[corbanb 🐻 @corbanb]

Remote Control is huge. Finally can take walks while Claude builds 🚶‍♂️ Build in the morning, review at night. Game changer.

[corbanb 🐻 @corbanb]

Claude Code just dropped Remote Control 😎 Start a session on your laptop, continue from your phone while walking your dog. The future of coding isn't at a desk.

[corbanb 🐻 @corbanb]

The 1000x engineer isn't the one who codes fastest. They're the one who can: Write specs at scale. Orchestrate 50 agents. Hold business context in their AI stack. The bottleneck moved - it's not writing code, it's architecting.

[corbanb 🐻 @corbanb]

The best developers aren't writing more code - they're writing better instructions. Prompt engineering isn't a buzzword, it's the new debugging. If your AI keeps making the same mistake, you haven't written the rule yet.

[corbanb 🐻 @corbanb]

Claude Opus 4.6 building complete mobile apps in 5 minutes for $0.17 is wild. We're entering the era where "build an app" goes from months to minutes. The real question: what do we build when anyone can build anything?

[corbanb 🐻 @corbanb]

@lydiahallie Ok this is so fun. Thanks for the work @lydiahallie and the @claudeai team!

[corbanb 🐻 @corbanb]

Let's see what you got cooking!

[corbanb 🐻 @corbanb]

Lets gooo!

Sadly the context window is having issues already. I can't get even a 10 page .md into chat yet.

[Claude @claudeai]

Introducing Claude Opus 4.6. Our smartest model got an upgrade.

Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes.

It’s also our first Opus-class model with 1M token context in beta.

[corbanb 🐻 @corbanb]

The AI coding wars just got interesting again.

OpenAI dropped something new. It's not quite Cursor, not quite Claude Code.

My take: UX wins now. The model is table stakes. The winner is whoever makes it feel like a partner, not an autocomplete. Combines engineering and UX/UI that stays modern. Shares learnings to make us smarter and not just taking directions but a real partner of thought.

What's your pick?

#Codex #claudecode #cursor #Engineering

[Sourav Ghosh @souravghosh]

It is probably the most underrated AI voice‑typing and dictation tool available.

For a one‑time payment of $29, it’s one of my best technology investments—not just this year, but in recent years as well.

Other tools with the same purpose charge $20 or more per month.

I’ve always missed having this on my iPhone.
After spending five minutes on the iOS app, I found its free version clearly outperforms the free versions of all other iOS apps I’ve tried this year.

@JoshiPax is 💎

[corbanb 🐻 @corbanb]

@majorityfm @SenSchumer and @RepJeffries SERIOUSLY! END THIS!!

[corbanb 🐻 @corbanb]

@Whizz_ai Course

[corbanb 🐻 @corbanb]

@samruddhi_mokal Gemini

[Samruddhi Mokal @samruddhi_mokal]

Gemini 3 has a capability most people don't even know exists.

it's not the 1M tokens.
it's not the multimodal processing.

it's something else entirely.

And it's the reason I built 3,000+ prompts specifically for Gemini 3.

Everyone talks about Gemini's specs:
→ 1 million token context
→ Native multimodal inputs
→ Deep Think mode
→ Agentic workflows

But they're missing what happens when you combine these features.

The secret is persistent systems thinking.

Gemini 3 doesn't just process large contexts.

It maintains coherent reasoning ACROSS those contexts while simultaneously:
- Analyzing images
- Reading documents
- Planning multi-step workflows
- Adapting based on previous outputs

This creates emergent capabilities that don't exist in other models.

I built 3,000+ prompts that exploit this.

Each prompt is built around this core insight:
Gemini 3's real power isn't WHAT it can process.
It's HOW it connects everything together.

The library includes:
✓ 3,000+ production-ready prompts
✓ Organized by difficulty (beginner → advanced)
✓ Real use cases for each prompt

Like, RT + reply "GEMINI" and I'll DM you the guide.
(Must be following so I can DM)

Skip this and keep wondering why your Gemini results feel the same as ChatGPT.
Or grab the library and start using the capability everyone's missing.

[corbanb 🐻 @corbanb]

@v0 Let’s go!

[corbanb 🐻 @corbanb]

Arrive 20 mins early. But don’t drink anything. You can’t leave!

[Dan Shipper 📧 @danshipper]

Yesterday, Microsoft rolls out MCP support to Windows.

Today, Google officially supports MCP in the Gemini SDK.

It's over, MCP wins.