Daniel Gräfe, the developer of Timing, has his own take on artificial intelligence with Cotypist, a unique approach to text completion on your Mac. In this video, I share the results of my time using the app and explain how to best take advantage of it.… This is a post for the MacSparky Labs Early Access and Backstage Access members. Care to join? If you’re already a member, you can log in here.
Cotypist: AI Autocompletion Everywhere on Your Mac
There are a lot of angles to AI and productivity emerging right now. One I’ve come to appreciate is AI-based smarter autocomplete. My tool of choice for this is Cotypist. It’s made by a trusted Mac developer, it’s fast, and it takes privacy seriously.
Unlike many AI writing tools that require you to work within their specific interface, Cotypist works in virtually any text field across your Mac. Whether you’re drafting an email, writing in your favorite text editor, or filling out a form, Cotypist is there to help speed up your writing.
The app’s latest version (0.7.2) brings notable improvements to both performance and completion quality. It even respects your Mac’s Smart Quotes preferences – a small but meaningful touch that shows attention to detail.
With Cotypist turned on, it offers inline completions that appear in real time. Then you’ve got a few options:
- You could just ignore the suggestion and keep typing like you’ve always done.
- If you want to accept the full multi-word suggestion, you press a user-defined key. (I use the backtick – just above the Tab key on a US keyboard.)
- If you just want to accept the next suggest word, you hit another user-defined key (I use Tab)
- If you want to dismiss the suggestion entirely, press escape. (This is handy when doing online forms, for instance.)
At first, the constant suggestions may feel distracting, but once I adapted to it, I can’t imagine going back.
Cotypist generates all completions locally on your Mac. No cloud services, no data sharing – just your Mac’s processing power working to speed up your writing.
Like I said, Cotypist represents an interesting take on AI and is worth checking out.
The Gen3 AI Revolution
I’ve been spending a lot of time with Claude 3.7 Sonnet lately, and I wanted to share some thoughts on the new “Gen3” AI models. Claude 3.7 is trained with a massive leap in computing power compared to its predecessors.
What’s Different About These New Models?
These new AI models aren’t just incrementally better; they represent a significant jump in capabilities.
There are two reasons for this:
- Training Scale: These models use 10x more computing power in training than GPT-4 did.
- Reasoning Capabilities: These models can spend more time “thinking” through complex problems, similar to giving a smart person extra time to solve a puzzle.
My Experience with Claude 3.7 Sonnet
I’ve been using Claude 3.7 regularly. Most folks use programming tests to baseline the AI models. I don’t. Instead, I’ve found it to be an exceptional thought partner. One of my favorite workflows is to give Claude something I’ve written and ask it to pose thoughtful questions about the content. Those questions often spark new ideas or help me identify gaps in my thinking.
For those of you who work alone without colleagues to bounce ideas off of, these more capable AI models can provide surprisingly useful feedback. It’s like having a smart colleague who’s always available to help you think through problems. As AI becomes capable of higher-order thinking tasks, there is a lot of room for us to be creative in how we put them to work.
The Human in the Room
You still need to be the human in the room. As smart as these models are getting, you’re making a mistake if you believe they’re actually thinking. They remain tools — increasingly powerful tools — but tools nonetheless. Your judgment, creativity, and ethical sensibilities remain irreplaceable. The most powerful approach is using these AI partners to amplify your thinking, not replace it.
If you’re curious about these Gen3 models, my recommendation is simple: experiment. Ask Claude to help you brainstorm solutions to a problem you’re facing. Have it review something you’ve written and suggest improvements. Use it as a sounding board when you’re trying to think through a complex issue.
You might be surprised at how helpful these conversations can be, even if you’re not using the flashy coding capabilities that get most of the attention.
I’m cautiously optimistic about where this is heading. These tools are becoming genuine intellectual partners that can help us think better, create more, and solve harder problems. Used wisely, they have the potential to dramatically enhance what we can accomplish.
The Lab Report for February 28, 2025
In this week’s episode of The Lab Report: A new app by John Siracusa, the M4 MacBook Air might be here very soon, and is Gemini coming to Apple Intelligence?
… This is a post for MacSparky Labs Members. Care to join? Or perhaps you need to sign in?
DEVONthink – Your Research Command Center (Sponsor)
One question I frequently get from MacSparky readers and MPU listeners is: “What’s the best tool for managing research on the Mac?” My answer is always DEVONthink, and this week I’m happy to have them as a sponsor.
Let me tell you about my favorite new feature: the Mentions inspector. Think of it as your digital librarian that automatically discovers connections in your research. When you select a document, Mentions shows you everywhere its title appears across your database, complete with context. I’ve found this invaluable for uncovering relationships in my research that I didn’t even know existed.
But that’s just scratching the surface. Here’s what makes DEVONthink my go-to research tool:
- Its AI engine learns how you organize and helps file new documents
- A powerful search language that lets you construct precise queries
- Rock-solid sync across devices with end-to-end encryption
- Smart rules and reminders to automate your workflow
- Rich AppleScript support for deep automation (I use this constantly)
The DEVONthink team keeps pushing the envelope with thoughtful improvements. Recent updates have brought enhanced PDF annotation, seamless Evernote import capabilities, and expanded Markdown support. This continuous evolution is why DEVONthink remains central to my research workflow.
If you’re looking to level up your research game, DEVONthink is offering MacSparky readers a 20% discount. It’s the tool I trust with my own research, and I think you’ll find it just as indispensable.
Focused 224: Chasing Valuable Rabbits, with Chenell Basilio
Chenell Basilio joins Mike and me on this episode of Focused to talk about cultivating curiosity, finding your people, and avoiding burnout.
This episode of Focused is sponsored by:
iOS 18.4 Beta New Features
At long last, the iOS 18.4 beta is out. Hooray! It doesn’t have the anticipated Apple Intelligence features (Boo!).
Nonetheless, there are some interesting new additions heading your way. I share them in this video.
… This is a post for MacSparky Labs Members. Care to join? Or perhaps you need to sign in?
Why the C1 Chip Matters More Than You Think
The iPhone 16e launch last week came with an understated but significant advancement: Apple’s new C1 communications chip. This custom silicon represents years of development, finally replacing the Qualcomm modem that has powered iPhone communications for generations.
For Apple, this marks another crucial step toward complete vertical integration of their hardware stack.
Developing a communications chip for the iPhone was no small achievement. It required extensive research, testing, and regulatory compliance – which explains why Apple has taken their time getting it right. Seeing the C1 chip finally shipping in a real iPhone feels like a significant milestone in Apple’s silicon journey.
However, the real test lies in its performance. Even those not interested in the iPhone 16e will be watching closely to see how well it handles its core function as a cellular device. Apple appears to have made a strategic decision by debuting the C1 in a lower-volume iPhone model, allowing them to gather real-world data and refine the technology before implementing it in the mainstream iPhone 17 and 17 Pro models.
Looking ahead, the C1 chip opens up intriguing possibilities for Apple’s broader ecosystem. Now that they’ve developed their own communications silicon, the natural question becomes: when will we see the C1 make its way into the Mac lineup? With Qualcomm out of the picture, I feel that is much more likely.
Mac Power Users 785: First of All, I’m David Sparks
On this episode of Mac Power Users, Stephen and I talk about failed purchase migrations, talk more about notifications, experience the power of old-school blogging, and discuss something new in the Sparks driveway.
This episode of Mac Power Users is sponsored by:
- 1Password: Never forget a password again.
- Google Gemini: Supercharge your creativity and productivity.
- Ecamm: Powerful live streaming platform for Mac. Get one month free.
- Incogni: Take your personal data back with Incogni! Use code MACPOWERUSERS with this link and get 60% off an annual plan.
Apple Disables Advanced Data Protection in the UK
In another chapter of its ongoing battle with the UK government, Apple has pulled the plug on Advanced Data Protection for UK customers. In a statement, Apple explained, “We are gravely disappointed that the protections provided by ADP will not be available to our customers in the UK…”
Instead of complying with the UK government’s demands for a system backdoor, Apple opted to completely disable the Advanced Data Protection feature for UK users.
The big question remains: Is this move enough to satisfy the UK government? We don’t know if this is a strategic play by Apple or if it represents a negotiated agreement between the two parties.
This story isn’t over yet. Meanwhile, UK citizens looking to keep their data private are left holding the bag.