Forem: With Attitude

I Asked Perplexity Computer for a Palantir Tearsheet, and 7 Minutes Later I Had a Bloomberg. And a Concern.

With Attitude — Wed, 06 May 2026 08:23:01 +0000

Perplexity Computer for Professional Finance launched May 4. I tested it on Palantir. The output was magnificent. The death of prompting is the part that should worry you.

Bloomberg: roughly $32,000 a year.

An old-school, command-heavy, terminal screen that looks like a microwave. But the terminal was never the moat.

The data Bloomberg uses is often public. So the data wasn’t the whole moat either.

The moat was the assembly: putting fragmented information, workflows, alerts, charts, filings, transcripts, context, and muscle memory into one place so professionals could understand markets faster.

Continue reading on Substack →

The Exact Prompt to Fix "My AI Tool Can't Access My Localhost"

With Attitude — Sun, 03 May 2026 14:45:00 +0000

Why your AI agent is blind to localhost (and 3 ways to fix it)

AI Product Manager and builder.
I write Product with Attitude, an AI newsletter of 18,000+ subscribers building with AI and developing critical AI literacy through practice.

The kind where you sit down on a Saturday morning, follow a guide,
and walk away with a working agent, automation, or product.

Built by you. Understood by you. Owned by you.

If you’re new here, welcome! Here’s what you might have missed:

Continue reading on Substack →

What Is A Sandboxed Virtual Machine?

With Attitude — Sun, 03 May 2026 14:44:25 +0000

Beginner-friendly infographic: Sandboxed VMs explained without jargon.

AI writers use “sandboxed” with the swagger of a term that needs no introduction.

I did that too, until someone pointed out the obvious: it absolutely does.

Many readers are not familiar with the concept.

Today, we’re going to fix that.

AI Product Manager and builder. I write Product with Attitude, an AI newsletter of 18,000+ subscribers building with AI and developing critical AI literacy through practice.

Continue reading on Substack →

Are You a Vibe Coder? Don’t Ship Straight Into the Provider Trap

With Attitude — Wed, 29 Apr 2026 05:34:01 +0000

For my fellow builders: go compliance-native before 2 August 2026.

Thousands of builders wrapped a frontier model in their own UI, added a logo, and started selling subscriptions.

With vibe coding, all of that can happen in a day.

If you’re one of these builders,Article 3(3) of the EU AI Actmade you the provider that day.

OpenAI, Anthropic, or Google still remain responsible for the general-purpose AI model they created. But you became responsible for the product you built on top of that model. And if your use case touched Annex III, you inherited every high-risk obligation in the regulation.

Continue reading on Substack →

Is GPT-5.5 Reliable For Citations? No. It’s The Worst Flagship For That Job.

With Attitude — Sat, 25 Apr 2026 05:11:44 +0000

The one GPT-5.5 benchmark OpenAI didn’t put in the launch post and why it matters for your critical AI literacy.

GPT-5.5 launched April 23, 2026.

It tops every benchmark that matters for builders.

Terminal-Bench. OSWorld. GDPval. ARC-AGI-2. Long-context MRCR. A real jump.

It’s also the most confidently wrong flagship on the market.

If you’re new here, welcome! Here’s what you might have missed:

→Claude Design Review: 48-Hour Builder’s Test + Hero Prompts

→I Mapped the Opus 4.7 Release to Your Role, Goals, and Real Workflows

Continue reading on Substack →

Claude Design Review: 48-Hour Builder's Test + Hero Prompts

With Attitude — Thu, 23 Apr 2026 12:00:09 +0000

I spent 48 hours testing Claude Design on Opus 4.7. The prompts, the credit traps, and why the "Figma is dead" take is louder than it is true.

I barely finished drafting theClaude Opus 4.7 reviewbefore Anthropic introduced Claude Design.

In 48 hours, I test and publish; in the same 48 hours, Anthropic ships a product, then another, and moves on.

From a product strategy perspective, the real story is not the design tool itself, but the stack Anthropic is building around it. Design, code, research, and memory are no longer separate experiences.

Continue reading on Substack →

I Mapped the Opus 4.7 Release to Your Role, Goals, and Real Workflows

With Attitude — Fri, 17 Apr 2026 08:05:45 +0000

Opus 4.7 Cheat Sheet for AI Learners, Writers, Knowledge Workers, Vibe Coders & System Builders

I see three main problems with the post‑launch flood of newsletters and media on new Anthropic models:

Continue reading on Substack →

Discounts for Premium Members (Q2 2026)

With Attitude — Thu, 16 Apr 2026 11:11:28 +0000

Your PwA subscription pays for itself in tool discounts and credits.

Updated April 2026· Actively maintained

Continue reading on Substack →

Everything I Can Offer You In Q2.

With Attitude — Thu, 16 Apr 2026 11:10:52 +0000

One year of building in public, 17K-member AI newsletter community, three built-in products, and discounts that make your Substack paid subscription a no-brainer.

When I started Product with Attitude 13 months ago, the goal was simple: learn in public by writing. Push further into AI product building. Research harder.

I was convinced I was writing for Product Managers, because who else would read this?

And then the first REAL writer joined our Community Chat.

I panicked.Was she lost? What could I possibly offer her?

Continue reading on Substack →

I Tested Atoms, Lovable, and Replit. One of Them Solves the Problem That Kills Most Apps.

With Attitude — Mon, 13 Apr 2026 19:23:51 +0000

A test-driven review of Atoms.dev, the multi-agent AI platform for solo founders. Includes Atoms vs Lovable vs Replit comparison and a live SEO/AIO/GEO experiment.

The failure data for vibe coded apps is brutal:

All of this gets defined before writing code and every platform that supports vibe coders from that perspective is more than useful - it’s overdue.

That’s one of the reasonsAtomscaught my attention even before their team reached out and asked for a test-driven review.

The other is that Atoms has been taking GitHub by storm. Despite launching in early 2026, it already has over 1M users.

Continue reading on Substack →

I Built a Claude Cowork Loop That Improves Itself. Here's the Exact Setup.

With Attitude — Thu, 09 Apr 2026 06:33:17 +0000

Anthropic slipped Cowork’s most interesting behavior into a support article. I turned it into a Karpathy-inspired system that gets smarter without writing a line of code.

TL;DR
Cowork Self-Improving Loop = Karpathy Auto-Research pattern + recurring tasks.

Somehow, Anthropic managed to hide Cowork’s best kept secret in a support article about recurring tasks.

Very few people seem to know about it, and I haven’t seen anyone intentionally building on top of it.

This guide is my attempt to change that.

By the end, you’ll be running a self-improving loop I built on top of Karpathy’s Auto-Research Pattern, adapted for Cowork.

Continue reading on Substack →

What AI Builders Are Shipping in the PwA Community Right Now

With Attitude — Tue, 07 Apr 2026 07:36:20 +0000

Product with Attitude is evolving from newsletter to builder lab. Here’s the new creator showcase format spotlighting what this AI community ships.

I can’t keep up anymore.
There’s so much being built inside this community that deep dives on every project stopped being realistic weeks ago.

It’s a beautiful problem to have.

This publication has evolved into something bigger than a newsletter.
It's a lab now.
People testing ideas in the open, shipping real things, expanding what AI can be used for, beta testing for each other.

Continue reading on Substack →