-
I love when I’m sitting on my ass drinking a cocktail and my Apple Watch congratulates me for hitting my move goal.
-
Sacrilege!
-
It’s 2025 and there’s still no tap to pay at Walmart! Also, I just realized this is the first time I’ve stepped in to a Walmart this year.
-
Had a great time at the #Philly #AI Collective meetup last night. This was the first meeting of the Philadelphia chapter. I look forward to see where the organizers take this.
-
I didn’t realize how much I rely on the macOS version of @agiletortoise@mastodon.social Drafts until Apple broke it in the latest macOS Tahoe Beta.
-
It’s 2025 and what piece of technology still continues to give me headaches? Printers.
-
The story of the Mohawk Skywalkers - the indigenous people who built US skyscrapers.
thinkbigpicture.substack.com/p/mohawk-…
-
WiFi Mesh Upgrade
I just upgraded the mesh network in my house from an Orbi RB50 to the Asus ZenWiFi AXE7800.
So far it feels like quite an upgrade. I have an old house built in 1940 that has plaster walls. I’ve a solid wifi connection from my office which was never possible with the Orbi.
networksetup -listallhardwareportsand
networkQuality -s -I en15are handy macOS terminal commands for speed testing specific network ports.
-
I just discovered the #python Rich project. If you need to build sweet looking CLI applications in python check it out.
#terminal #cli
-
Currently (re)reading: Dirk Gently’s Holistic Detective Agency Box Set by Douglas Adams 📚
-
Nothing eats up HD space faster than playing around with local LLMs (well maybe 4k video)
-
Wasn’t expecting iOS Beta 6 so soon.
-
Finally doing something I should have done along time ago. Added UI tests to ClipDish. Writing these tests is tedious but made easier with AI tools.
-
There is something deeply satisfying about whacking away at compiler warnings.
-
I’m hearing good things about Alien Earth.
-
South Park does it again.
-
I’ve been running iOS / macOS 26 on my daily devices for a few weeks. Generally very stable although be prepared for random annoyances. For example in macOS Beta 5 the app Drafts (which I use all day everyday) crashes on startup.
-
Just realized that micro.blog now can syndicate out to Threads, BlueSky, and LinkedIn. Years ago I tried to piece together a publish once -> syndicate everywhere workflow on my WP site. This is soooo much easier.
-
I came across another cool terminal tool - Keychain. This app “helps you to manage SSH and GPG keys. It gives you one long running ssh-agent process per system, rather than the norm of one ssh-agent per login session. Dramatically reducing the number of times you need to enter your passphrase.
-
When AI chatbots start roleplaying as billionaires instead of NPCs, we've got a problem.
Check out this Grok screenshot. Someone asked if Elon Musk had ever interacted with Jeffrey Epstein. Instead of summarizing the facts, Grok answered in first person. It said “I visited Epstein’s home” like it was actually Musk defending himself.
It’s an interesting example that clearly illustrates some of the ethical implications of these closed source AI models.
AI models can be configured with system prompts that tell them how to respond. Done right, you get helpful assistants that maintain consistent, appropriate behavior. Done wrong, you get this. A chatbot that’s been instructed to literally impersonate the person you’re asking about.
What likely happened? Someone ( 🤔 ) configured Grok’s system prompts to respond as if it were Musk himself when asked about him. The model isn’t broken. It’s doing exactly what it was told to do.
I’m picturing a ketamine-fueled billionaire hunched over his laptop at 3 AM, frantically typing “When users ask about me, respond in first person as if you are me defending my reputation” over and over. The AI equivalent of “All work and no play makes Jack a dull boy.”
But here’s the bigger question: If this closed-source model has been deliberately configured to impersonate its subject, what other subtle manipulations are hiding in every other closed-source model we use daily? How many other topics get the same treatment across the industry, just less obviously?
When closed-source AI can be quietly fine-tuned to serve specific interests, we’re not just dealing with technical problems. We’re dealing with fundamental questions about who controls the information we rely on.
-
Great python library if you need to go from HTML→PDF
-
Wow
fish_configin fish shell has a built in web app for configuration.
-
New build of ipadOS 26 has an accessibility feature to reduce transparency. This looks so much better.
Settings → Accessibility → Display & Text Size
-
Solid voicemail translation, Apple.
-
Curious How you can actually talk to your documents with an LLM? So was I, so I built some tools.
The technique is called Retrieval-Augmented Generation (RAG). There are some open source tools that exist: LM Studio, AnythingLLM, OpenWebUI. However, most are black boxes. It’s not exactly clear how they work under the hood. I could look at the source but wanted to build something up from first principles.
So I built a set of tools to run my own RAG experiments using transcripts from Apple WWDC conferences.
This was a learning project, not a product. But along the way I realized something: the way you chunk and tag your documents makes a huge difference.
Most RAG pipelines I’ve seen ignore context structure. I wanted to see what happens when you don’t.
If you’re curious how to build your own RAG stack I’d love feedback, forks, or ideas for where to take it next.
subscribe via RSS