In light of the recent mess around AI use in the US government, I figured it was time to wonder how Claude might feel about it all. 🙃
www.alicealexandra.com/blog/clinic...
In light of the recent mess around AI use in the US government, I figured it was time to wonder how Claude might feel about it all. 🙃
www.alicealexandra.com/blog/clinic...
Perplexity Computer is so close to being amazing.
I've been using it heavily this week. Here's my unfiltered thoughts about where I find it most useful and where it still falls short.
builder.io/blog/perple...
being a devrel in the AI era means writing a blog post that becomes outdated before you can publish it.
cannot tell you how often this happens.
A graph shows a decline in developer sanity as the number of AI agents increases, with a call to "stop the decline" alongside.
Running multiple AI agents gets ridiculous fast.
- You have 100 windows open
- Your computer fans are crying
- Agents keep bonking into each other in the code
- You can't ever shut the laptop, which makes it tough to just... have a life
Here's how to manage the chaos: builder.io/blog/ai-age...
Subagents are super powerful when you grow out of skills.
They're also really tough to debug.
Here's all my tips and tricks for wrangling and optimizing them.
www.builder.io/blog/subagents
If you're running out of steam on your Lovable prototype, here's all my favorite alternatives.
www.builder.io/blog/lovabl...
My entire timeline is full of people using Clawdbot, and they all kinda sound like this to me.
www.alicealexandra.com/blog/the-200...
I've experimented a ton with skills, commands, rules, and subagents.
Here's my best advice on when to use each pattern and how to optimize.
www.builder.io/blog/agent-...
We keep saying the tech industry is losing its junior devs to AI, but there's a more nuanced take:
Vibe coders are the next generation of juniors.
In my technical writing these days, I'm thinking a lot about how I can teach and meet these newcomers where they are.
In OpenCode, I've even made it a command: /survey:
"How was working in the codebase today? Did anything trip you up with how things are organized? Are there refactors needed? Did your tooling let you do everything you needed today?"
A helpful tip for AI coding: after a long task is complete, ask the agent how working in the codebase went.
Then, turn any recurring feedback into issues for later agents to look into.
This helps keep your codebase cleaner. Agents know what context they need that they're not getting.
Cursor's visual editor is cool for solo devs, but on a team, devs add zero value by moving a button 10px left.
Designers should own those changes.
Here's how the new design mode works, and what still needs to change before Cursor can be a Figma killer.
www.builder.io/blog/cursor...
Personally, I think authors should be able to opt out of training on their works entirely.
If their work is used, they should get options for ongoing compensation based on actual AI usage. (Though we don't have accurate ways to measure usage yet.)
AI-generated scene of a futuristic server room with glowing blue humanoid figures made of data holding open books, while more books float above a floor of streaming code; two books are stamped “PIRATED EDITION,” and the word “Anthropic” glows on the back wall.
Anthropic agreed to pay $1.5B to settle claims it trained AI on millions of pirated books.
But the judge hasn’t approved it yet, questioning if $3,000 per book is the right precedent.
What do you think? Does this move us forward on fair compensation or just leave questions?
It would be nice if you could prototype with AI right on your live site...
...without hand-replicating the repo, knowing how to code, or migrating your entire stack.
And then send that PR right to your devs to approve.
Luckily, you can.
www.youtube.com/watch?v=8q3...
loving the DX of the new SvelteKit async updates.
the best frameworks don't hype. they cut away ceremony, so things like async just... feel like you think it should be.
fewer footguns, more flow. LLMs just "get it" reading the docs, too.
A doctored screenshot of a ChatGPT conversation. A user asks, "How much water do you use per query?" ChatGPT responds that it uses a very small amount, "roughly 0.32 milliliters." However, a line of red text has been edited in below this, humorously contradicting the official answer by stating, "This response used 100mL of water."
Cars have EPA window stickers and EU CO2 caps. AI has... "trust us, bro, it's fine."
We need enforceable ‘AI Energy & Emissions’ labels on every major model.
If you're shipping AI without evals, you're running prod on vibes.
At Builder, we wire evals into CI, A/B tests, and prod to catch regressions and prove AI feature upgrades actually help our users.
Here's how to set up your own.
www.builder.io/blog/ai-evals
A two-panel meme using stills of the main character from the TV show Squid Game. The top panel shows the character smiling gleefully with the caption, "watching ai generate code." The bottom panel shows the same character with a serious, stressed expression, captioned, "reviewing ai generated code."
Some tips for code reviews without the tears: www.builder.io/blog/code-r...
TDD feels bad. If I know how to write the function, why start with the spec?
But AI agents switch it up. They need guardrails, and tests let them iterate on even the most complex problems.
I'm convinced AI TDD is the way. Here's what changed my mind:
www.builder.io/blog/test-d...
So, does macOS 26 solve the bug where the Passwords app always opens behind your currently open app? I think that's all I care about for advancements.
looking at the sink: "ugh, time to do plate laundry again"
Reviewing 1000-line AI-generated diffs sucks. Even AI can't really do it right.
Here's how to stop being an AI babysitter and start being a code architect.
www.builder.io/blog/code-r...
Copy/paste from any website into your own design system with Fusion: www.builder.io/blog/mock-u...
you gotta scrape OpenAI back sometimes
Keeping Figma in sync with Storybook (and your entire design system) just got way easier.
Weird anti-AI scraping technique: digital tar pits.
Websites hide links that lead bots to an endless maze of auto-generated gibberish that all link back to itself, poisoning training data.
Wouldn't recommend, but still an interesting tactic against overly eager scrapers.
Figma's *official* Dev Mode MCP server is now in open beta, and it's a pretty awesome tool!
I've updated this article with how best to use it, how its AI works under the hood, and where some alternate workflows can augment your design to code process.
www.builder.io/blog/figma-...
sometimes when i listen to Hozier, i'm just like, "Andrew, stop it, we're in _public_"