Joshua Wood

Microblog

Watching National Treasure in honor of America’s 250th birthday. 🇺🇸

Spending the first couple days catching up on life things I was neglecting… switched insurance providers, got a bid to fix the roof, did some organizing.

I’m taking some time off from work to recharge this summer, very much appreciate my team for making this possible. (source)

I’m taking some time off from work to recharge this summer, very much appreciate my team for making this possible.

No one told me InfoWars is doing guests, I could be the second member of my family to be on InfoWars.

Good news, folks. We have closed all the gaps. There are no more gaps left to close. Might as well take the day off. Happy Friday!

It’s always funny to me when our VC/PE-backed competitors target us directly in their marketing. Like we’re five people, bro. You should probably be concerned that you think about us at all.

“The reason I’ll never forget Jon is he wrote his name on my shoe.“ —8yo on last day of school

Is Honeybadger building another agent?

We’ve been thinking a lot about AI and the future of application monitoring at Honeybadger. The past few years have been chaotic, fascinating, and everything in between.

Many in the industry claim that the future is agentic everything, but no one knows what the future holds. We’re still figuring this out just like you.

One thing is clear: AI is extremely useful for monitoring and debugging.

But our goal is the same as it’s always been — to cut through the noise and continue delivering the human-centric product and support that we have for 14 years.

So no, we’re not building another agent. Instead, we’re providing structured, queryable, signal-rich data that works with your existing LLMs and automation so that you (and your agents) can get to the root cause faster.

Does this resonate with you?

PS: We reject the idea that AI will replace developers. If anything, skilled developers are more important than ever. We’ll always be on the side of developers.

On day 2 of decaf and feel fine. I tapered to half caff in the morning for three or four days first. Headache was actually not bad. Definitely feels calmer so far.

Thinking about quitting coffee/caffeine. Has anyone done this? (source)

Software leaders on LinkedIn are starting to talk about the growing quality crisis in agentic engineering and they’re like, “It’s not just a crisis, it’s a five-alarm bill that’s coming due. The gap between…”

If I see one more slop post capitalizing on the growing quality crisis in agentic engineering, I’m going to lose my mind. This shit is affecting real people. The least you can do is take the time to say it yourself.

Thinking about quitting coffee/caffeine. Has anyone done this?

I wrote a little Ruby script today by hand. It was fun and rewarding, I recommend it.

I wish I could get my kids to ELI5. Explain it like I’m five, not explain it like you’re five!

I am currently editing our company blog after our last editor left, and realized some AI content was slipping through. So now we have a policy for authors. A few thoughts:

As a reader, slop is cringe. When I have the feeling that something is AI-generated, I nope out immediately. Everyone I’ve asked does too. (If I know you and you’re doing this, oof.)

If it’s not immediately obvious but I realize you’ve tricked me, I am now physically mad at you. You wasted my time. I will go out of my way to avoid your content in the future.

We’ve also found that when authors start with AI in their writing process, it makes it nearly impossible to edit or provide review feedback. The logic of the piece is just a disjointed mess. The only feedback I can give is to throw it away and start over.

For these reasons, we do not allow our authors to use generative AI for content. We do allow very limited use for research and codegen, but that’s it.

Honestly, if you consider yourself a writer and you use AI to generate your words, you are not a writer.

I’m watching this cycle burn through some of the best people I know. It fucking sucks.

Erika Hall: What I’m hearing from friends and colleagues in tech companies is the most insane shit I’ve ever heard. Organizations are fucking up previously functional workflows and operating models, ditching workers, and adding unpredictable costs out of mass FOMO with no plan. (source)

Fun fact: Kagi does this too, but you can turn it off! Although now I kinda wish they let you customize the system prompt for real.

A kagi quick answer screenshot: Oh, look at this. You’re asking about Honeybadger.io, and honey badger? He don’t care. He don’t give a sh*t. But since you’re asking, Honeybadger.io is this little piece of tech that’s actually pretty smart, unlike those other nasty creatures in the wild. It’s an error tracking and application monitoring tool that sits there and watches your code like a hawk—or a badger, I guess—to make sure everything is running smooth. Here’s the breakdown of what it does: It tracks errors: When your application decides to go crazy and break, this thing catches it immediately so you don't have to go hunting for it in the dark. It monitors performance: It keeps an eye on how your app is behaving, making sure it’s not acting all sluggish or nasty. It helps you fix things fast: It puts everything in one simple interface, so you can swoop in, fix the problem in record time, and get back to doing whatever it is you do. It’s basically the honey badger of the software world—it’s fearless, it’s efficient, and it gets the job done without any of the drama. Now, get out of here. kagi search AI features settings page

When a coder gets hungry (source)

People keep talking like AI is inevitable. Idk man. It’s not going great and we haven’t even entirely forgotten how to code yet.

This morning I’m depressed, thinking about quitting tech entirely. Then I get lucky with Claude and feel like a million bucks. I’ve felt like this before and it required rehab.

I feel like a genius for flying out of SNA instead of LAX

I’m in Long Beach for PyCon US for a few days. Would love to say hello if any internet friends are here!

Do I know any good freelance technical content editors who love developer tools and hate AI prose with the fire of a thousand suns?

I love my kids and wouldn’t trade them but what would it be like if they didn’t consume my best brain cells each morning.

Nice weather lately but idk why you’d rather be outdoors, I love reviewing this slop

Output isn’t design

Writing helps clarify thought because the act itself forces you to organize it. […] Design works the same way for me. The value is not only in the output. It is in the gradual understanding that comes through doing the work.

atproto and lexicons are cool because they make your personal data portable. It’s trivial to switch to a different app that uses the same lexicon, or you could build your own.

journalists: “here’s what the footgun had to say about the unfortunate incident with the foot”

“You’re absolutely right. I will update my memory to never shoot your foot again.”

—a gun pointed at your foot (source)

claude fact checked this post: it’s actually 80% MLM and 30% genuinely useful

AI is 80% multilevel marketing scheme, 20% genuinely useful technology (source)

AI is 80% multilevel marketing scheme, 20% genuinely useful technology

“You’re absolutely right. I will update my memory to never shoot your foot again.”

—a gun pointed at your foot

asking the gun why it shot them in the foot: “did you just shoot my foot? BE HONEST” (source)

asking the gun why it shot them in the foot: “did you just shoot my foot? BE HONEST”

reading primarily LLM output is a problem. people write like they read