This week’s AI Engineering World’s Fair just posted my talk on the agony and ecstasy of voice in, visuals out agents. It’s a challenge to get model responses that feel immediate, but when it works, it feels magical.
Hi, I’m Allen Pike. I’m currently building Cedarloop, hosting It Shipped That Way, and writing monthly about what I’m learning.
Link: Voice In, Visuals Out @ AI Engineering World’s Fair
Link: Surprise! Pay $1000
My turn writing for the Forestwalk blog:
Now typically, when you try a SaaS product for free without a credit card, and you hit the limit, you get cut off. Also known as “disruption to your service”. Instead, we were invoiced $1000, which was immediately overdue.
Genuinely curious how common this practice is. Just because I was surprised by it, doesn’t mean it’s unheard of.
Link: Test Coverage Won’t Save You
Forestwalk’s CTO Jenn Cooper shares what she’s been learning about tests, after a couple years of increasingly coding with agents:
Most discussions about AI-native development jump from this problem – agents’ tendency to accumulate tech debt – directly to tests. … Tests verify that code does what it did before.
Whether what it did was even the right way to do it is a separate question.
She argues that while agents make it easy to have rigorous traditional test coverage, at best unit tests maintain local code cohesion. At worst, they can actually make it harder to improve what agents are worst at: the wider coherence of the entire codebase.
So far I’ve been impressed with how effective the broader automated checks she describes can be to guard against agentic nonsense.
Building for Voice In, Visuals Out
Flashes of brilliance, and the tyranny of latency.
Recently, Andrej Karpathy argued that the ideal interaction pattern for AI models is voice in, visuals out: Audio is the human-preferred input to AIs, but vision is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision; it is the 10-lane...
We Can Do Hard Things
On getting uncomfortable.
Years ago, back when I was leading a mobile dev team, my friend had an idea for a business. You see, back then the most frustrating thing about mobile dev was the final step: getting your app on actual phones. Builds, provisioning, and code signing made for a harrowing trial,...
The Rise of Transparency
Finding signal in the firehose.
Small companies are, by default, very transparent. When there are 4 people working in a room, you have a direct line of sight on what everybody else is doing, and why. Your docs, Slack channels, and repositories are open to everybody. When the CEO has an epiphany that changes everything,...
Launch Now
On trading comfort for speed.
Inside us are two wolves. One wolf wants to craft, polish and refine – make things of exceptional quality. The other wolf wants to move fast and get feedback now. The two wolves don’t always get along. For years, I’ve balanced this by working toward exceptional products but constantly collecting...
Link: Maggie Appleton on Gas Town and Coding Agent Orchestration
Maggie was already perhaps the best writer on the intersection of engineering and design, but now that she’s joined Github Next, she’s also extremely keyed in to where tools for coding are going. Her piece on Gas Town and orchestrating coding agents is sharp and worth reading in full.
As the pace of software development speeds up, we’ll feel the pressure intensify in other parts of the pipeline: thoughtful design, critical thinking, user research, planning and coordination within teams, deciding what to build, and whether it’s been built well.
The most valuable tools in this new world won’t be the ones that generate the most code fastest. They’ll be the ones that help us think more clearly, plan more carefully, and keep the quality bar high while everything accelerates around us.
We’ve known for a couple years now that faster coding will mean non-coding work will increasingly be a bottleneck, and now it’s happening. Deciding what to build – and whether it’s been built well – was already one of the most important tasks on a software team.
But in the face of tools that can add anything to your product, desirable or not, this judgement becomes the core of the work.
A Broken Heart
Or, getting a 100x speedup with one dumb line of code.
You always know it’s a good bug when your first reaction is, “How could this even happen?” The other day, I was refining the dashboard of a web app we’re working on – as you do – and I noticed it was taking forever to load. Like, it had been...
A Box of Many Inputs
On browsers, local classifiers, and Roger Rabbit.
One of the interesting questions when designing AI-enabled software is, “What does search input mean?” This was once a simple question: if a user entered “squish” in a search box, it would of course return things that contained “squish”. Over time though, computers have improved to the point where a...
Link: Why is ChatGPT for Mac So… Bad?
Last week I wrote an exploration of Ben Thompson’s recent question, “Why is the ChatGPT Mac app so good?” A lot of people on the internet, it turns out, do not agree with this premise!
Many folks have been having problems with ⌘C not copying text. Hacker News sees the app as “not good at all”, to the point that my post about it being better than the alternatives was flagged off the site. X doesn’t like it either.
Beyond the bugs I mentioned in last week’s post, I’ve recently been plagued with a ChatGPT Mac bug of my own, where every time I start a new chat, it will pre-fill the text field with the first input I used last time I started a new chat on Mac.
All of this led me to an informative post by one of OpenAI’s Mac developers, Stephan Casas:
nearly everyone who works on the ChatGPT macOS app has been stretched thin, and hard at work building Atlas.
[…]
i’m thankful that our users appreciate our decision to develop a native app just as much as i’m thankful for the heightened expectations they hold because we did so
Apparently he merged a fix this week for the copy-paste bug that has been plaguing many folks, which is promising.
Something implied in last week’s article that’s worth saying explicitly: although many good Mac apps are native, being native is neither necessary nor sufficient for being a great app.
While OpenAI is investing more in desktop apps than any other model labs, they have much to do before they can transcend “better than the alternatives” and achieve “great.”
Why is ChatGPT for Mac So Good?
Claude, Copilot, and making a good desktop app.
This year, even as Anthropic, Google, and others have challenged OpenAI’s model performance crown, ChatGPT’s lead as an end-user product has only solidified. On the Dithering podcast last week (paywalled), Ben Thompson called out an aspect of why this is: I need someone to write the definitive article on why...