Anthony Panozzo

Was thinking about this today around blog email subscriptions vs. RSS. Email is kind of the lingua franca / lowest common denominator that, though it has flaws, allows you to send almost anything to anyone when you have their email address.

Love Boggle. Played a ton of Word Racer on Yahoo! Games back in the day.

Screenshot Web view on left Obsidian on right showing the same cards

FYI hacked something together in Claude Code, could be useful in an eventual solution.

GitHub - panozzaj/cc-usage: A Mac app that shows you your Claude Code current usage and usage history A Mac app that shows you your Claude Code current usage and usage history - panozzaj/cc-usage

The project, btw: github.com/panozzaj/cc-...

Have a few bug fixes that are blocked by some Tauri framework improvements that I haven't PRed upstream yet

Makes sense. I guess in that case it'd probably have to be something hosted somewhere (with sync like Dropbox?) and/or ngrok or tailscale or some other kind of tunnel to your machine. Also not as familiar with how the web view would work. So maybe not a good fit. I might poke around with it

Screenshot: want me to npm run restart to rebuild? * cogitated for 3m 9s > yes, always restart. this should be in your claudem.md * bash(npm run restart 2>&1 | tail -5) > cc-usage@1.0.0 open > open 'src-tauri/target/release/bundle/macOS/Claude Usage.app' [timeout 2m) * Recalled 1 memory (ctrl+o to expand) * The claude.md already says "always run npm run restart after making code changes." - I'll note it in my memory file so I don't forget. * Recalled 1 memory, wrote 1 memory (ctrl+o to expand) * App rebuilt and relaunched. Memory updated - 'i'll always restart without asking from now on.'

Might as well slap another couple of layers of memory to be sure

For personal, recently came across
bsky.app/profile/davi...

Seems nice since it has a card view. They are Markdown files under the hood so you can have Claude or whatever help. I am probably going to check it out more this week since I have a similar need.

For team use (collaboration features), or personal?

I just haggled with a chatbot We ordered a wood chest that arrived with cosmetic damage. After logging the damage in their customer support interface, it prompted me to start a chat with their AI virtual assistant. What happened next: 1. It immediately offered me a 15% refund to keep the product 2. I asked for 20% and it immediately agreed 3. I asked for 25% and it immediately agreed 4. I asked for 30% and it turned me down 5. I took the 25%, which was, indeed, immediately refunded Turns out that negotiating with a rules engine is way easier than negotiating with a human tasked with operating a rules engine.

I just haggled with a chatbot

I liked the concept of "atom moat". Seems true. And moat vs. force field. Thought it was really compelling due to him having seen several companies and comparing them. And closer to classic Yegge writing style

The Anthropic Hive Mind As you’ve probably noticed, something is happening over at Anthropic. They are a spaceship that is beginning to take off.

Anthropic operates a high-velocity "hive mind" with ≈90-day planning cycles, versioned workstreams, and claimed 10×–1000× developer productivity, enabling rapid productization such as Claude Cowork, launched publicly about 10 days after conception.

Has worked pretty well so far. Hopefully doesn't sound too Claude-y. I am pretty much learning several new things per day (even if it's short TIL kind of stuff) so the list is getting long. I looked at old drafts and ideas though and it's surprising how many are just obsolete now...

I had Claude look at my Jekyll blog and write a style guide, then a /blog-idea skill that takes either random musings or current conversation learning and turns it into an 80-90% good draft (with link to conversation.jsonl) Then I can refine/reword it and have it check it over.

Wow that is intense. I feel like at least once a day I'm blown away by what it can do or what things it comes up with, and this would surely qualify.

Yeah, I found that it does about a 90% good job of reviewing. And you can even reply to it to help it be better for future reviews or teach it about your codebase.

code.claude.com/docs/en/hook... + play the yt-dlp of www.youtube.com/watch?v=gsNa... audio is how I'd try it if so inclined

New blog post:

Building a /reload Command for Claude Code

panozzaj.com/blog/2026/02...

Wizard of Wor Reverse Engineering Project screenshot

I forgot to tell everyone that last month I used Claude Code to perform an experimental forensic analysis and disassembly of Wizard of Wor on Atari 800

You can find the files here!
www.bxfoundry.com/wor800/

I love it when I type in a well-crafted message to Claude Code, and it's like "...Hmm, it seems like you meant this for another project" and I'm like, "oh, yeah, you're right" and have to copy/paste it to the right project.

That's how I say it in my head at least.

my experience has basically been that i no longer get "i cannot make myself read or write code" burnout, i get "i cannot make myself think" burnout, since the bottleneck is basically how fast I can process what needs to be done

Sam Altman @sama It was amazing to watch how much faster we were able to ship 5.3-Codex by using 5.3-Codex, and fore sure this is a sign of things to come.

I expect AI increasingly helping to develop itself and speeding up progress will be one of the big storylines this year. Another key development will be progress with AI co-scientists in other fields besides computer science.

The singularity is getting nearer.

Yeah my dad and I (mostly dad) did the dryer heating element like 2 or 3 times. I saw a YouTube video with the washer repair but seems a bit finicky. Might buy one at some point, ours was used on Craigslist since the time we rented!

Yeah re-reading my initial message and it does look like washing machine!

Washer repair. I hunted through the manual and found a test mode that replicated my problem noise so I am pretty sure it is the drain pump. So that gave me a little more confidence in a fixer. But I don't want to mess with it since there's water. 16 years old so might be looking at some point...

GitHub - strangeloopcanon/ai-radio Contribute to strangeloopcanon/ai-radio development by creating an account on GitHub.

Just for fun I made an AI Radio app because it didn’t seem to exist.
github.com/strangeloopc...

The speed with which you can make stuff is honestly a little dizzying.

ACE-Step/Ace-Step1.5 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

I hacked on something very similar today with huggingface.co/ACE-Step/Ace...
And it was pretty impressive how fast it came together. Would be cool to put on a virtual DJ as well

Claude Opus 4.6 We’re upgrading our smartest model. Across agentic coding, computer use, tool use, search, and finance, Opus 4.6 is an industry-leading model, often by wide margin.

Opus 4.6 is out.

- Same price
- Focus on subagents
- 1m token context (beta), 128k output tokens
- Improved agentic search
- Adaptive thinking

www.anthropic.com/news/claude...

(This thread brought to you by a little background task I vibe-coded up to alert me when the changelog changes. Open to feedback or if you think it's useful / interesting.)

"Claude now automatically records and recalls memories as it works"

I definitely noticed this. It seems to just read/write to CLAUDE .md in the same way, although could swear I saw a MEMORY .md file in one of the projects I was working on last night.