This Week's Sponsor:

Inoreader

Build your own newsfeed and cut through the noise

Posts in notes

On MiniMax M2 and LLMs with Interleaved Thinking Steps

MiniMax M2 with interleaved thinking steps and tools in TypingMind.

MiniMax M2 with interleaved thinking steps and tools in TypingMind.

In addition to Kimi K2 (which I recently wrote about here) and GLM-4.6 (which will become an option on Cerebras in a few days, when I’ll play around with it), one of the more interesting open-source LLM releases out of China lately is MiniMax M2. This MoE model (230B parameters, 10B activated at any given time) claims to reach 90% of the performance of Sonnet 4.5…at 8% the cost. You can read more about the model here; Simon Willison blogged about it here; you can also test it with MLX on an Apple silicon Mac.

What I find especially interesting about M2 is that it’s the first model to support interleaved thinking steps in between responses and tool calls, which is something that Anthropic pioneered with Claude Sonnet 4 back in May. Here’s Skyler Miao, head of engineering at MiniMax, in a post on X (unfortunately, most of the open-source AI community is only active there):

As we work more closely with partners, we’ve been surprised how poorly community support interleaved thinking, which is crucial for long, complex agentic tasks. Sonnet 4 introduced it 5 months ago, but adoption is still limited.

We think it’s one of the most important features for agentic models: it makes great use of test-time compute.

The model can reason after each tool call, especially when tool outputs are unexpected. That’s often the hardest part of agentic jobs: you can’t predict what the env returns. With interleaved thinking, the model could reason after get tool outputs, and try to find out a better solution.

We’re now working with partners to enable interleaved thinking in M2 — and hopefully across all capable models.

I’ve been using Claude as my main “production” LLM for the past few months and, as I’ve shared before, I consider the fact that both Sonnet and Haiku think between steps an essential aspect of their agentic nature and integration with third-party apps.

That being said, I have been testing MiniMax M2 on TypingMind in addition to Kimi K2 for the past week and it is, indeed, impressive. I plugged MiniMax M2 into TypingMind using their Anthropic-compatible endpoint; out of the box, the model worked with interleaved thinking and the several plugins I’ve built for myself in TypingMind using Claude. I haven’t used M2 for any vibe-coding tasks yet, but for other research or tool-based queries (like adding notes to Notion and tasks to Todoist), M2 effectively felt like a version of Sonnet not made by Anthropic.

Right now, MiniMax M2 isn’t hosted on any of the fast inference providers; I’ve accessed it via the official MiniMax API endpoint, whose inference speed isn’t that different from Anthropic’s cloud. The possibility of MiniMax M2 on Cerebras or Groq is extremely fascinating, and I hope it’s in the cards for the near future.

AI Experiments: Fast Inference with Groq and Third-Party Tools with Kimi K2 in TypingMind

Kimi K2, hosted on Groq, running in TypingMind with a custom plugin I made.

Kimi K2, hosted on Groq, running in TypingMind with a custom plugin I made.

I’ll talk about this more in depth in Monday’s episode of AppStories (if you’re a Plus subscriber, it’ll be out on Sunday), but I wanted to post a quick note on the site to show off what I’ve been experimenting with this week. I started playing around with TypingMind, a web-based wrapper for all kinds of LLMs (from any provider you want to use), and, in the process, I’ve ended up recreating parts of my Claude setup with third-party apps…at a much, much higher speed. Here, let me show you with a video:

Kimi K2 hosted on Groq on the left.Replay

Read more

Anthropic Releases Haiku 4.5: Sonnet 4 Performance, Twice as Fast

Earlier today, Anthropic released Haiku 4.5, a new version of their “small and fast” model that matches Sonnet 4 performance from five months ago at a fraction of the cost and twice the speed. From their announcement:

What was recently at the frontier is now cheaper and faster. Five months ago, Claude Sonnet 4 was a state-of-the-art model. Today, Claude Haiku 4.5 gives you similar levels of coding performance but at one-third the cost and more than twice the speed.

And:

Claude Sonnet 4.5, released two weeks ago, remains our frontier model and the best coding model in the world. Claude Haiku 4.5 gives users a new option for when they want near-frontier performance with much greater cost-efficiency. It also opens up new ways of using our models together. For example, Sonnet 4.5 can break down a complex problem into multi-step plans, then orchestrate a team of multiple Haiku 4.5s to complete subtasks in parallel.

I’m not a programmer, so I’m not particularly interested in benchmarks for coding tasks and Claude Code integrations. However, as I explained in this Plus segment of AppStories for members, I’m very keen to play around with fast models that considerably reduce inference times to allow for quicker back and forth in conversations. As I detailed on AppStories, I’ve had a solid experience with Cerebras and Bolt for Mac to generate responses at over 1,000 tokens per second.

I have a personal test that I like to try with all modern LLMs that support MCP: how quickly they can append the word “Test” to my daily note in Notion. Based on a few experiments I ran earlier today, Haiku 4.5 seems to be the new state of the art for both following instructions and speed in this simple test.

I ran my tests with LLMs that support MCP-based connectors: Claude and Mistral. Both were given system-level instructions on how to access my daily notes: Claude had the details in its profile personalization screen; in Mistral, I created a dedicated agent with Notion instructions. So, all things being equal, here’s how long it took three different, non-thinking models to run my command:

  • Mistral: 37 seconds
  • Claude Sonnet 4.5: 47 seconds
  • Claude Haiku 4.5: 18 seconds

That is a drastic latency reduction compared to Sonnet 4.5, and it’s especially impressive when we consider how Mistral is using Flash Answers, which is fast inference powered by Cerebras. As I shared on AppStories, it seems to confirm that it’s possible to have speed and reliability for agentic tool-calling without having to use a large model.

I ran other tests with Haiku 4.5 and the Todoist MCP and, similarly, I was able to mark tasks as completed and reschedule them in seconds, with none of the latency I previously observed in Sonnet 4.5 and Opus 4.1. As it stands now, if you’re interested in using LLMs with apps and connectors without having to wait around too long for responses and actions, Haiku 4.5 is the model to try.

LLMs As Conduits for Data Portability Between Apps

One of the unsung benefits of modern LLMs – especially those with MCP support or proprietary app integrations – is their inherent ability to facilitate data transfer between apps and services that use different data formats.

This is something I’ve been pondering for the past few months, and the latest episode of Cortex – where Myke wished it was possible to move between task managers like you can with email clients – was the push I needed to write something up. I’ve personally taken on multiple versions of this concept with different LLMs, and the end result was always the same: I didn’t have to write a single line of code to create import/export functionalities that two services I wanted to use didn’t support out of the box.

Read more

Testing Claude’s Native Integration with Reminders and Calendar on iOS and iPadOS

Reminders created by Claude for iOS after a series of web searches.

Reminders created by Claude for iOS after a series of web searches.

A few months ago, when Perplexity unveiled their voice assistant integrated with native iOS frameworks, I wrote that I was surprised no other major AI lab had shipped a similar feature in its iOS apps:

The most important point about this feature is the fact that, in hindsight, this is so obvious and I’m surprised that OpenAI still hasn’t shipped the same feature for their incredibly popular ChatGPT voice mode. Perplexity’s iOS voice assistant isn’t using any “secret” tricks or hidden APIs: they’re simply integrating with existing frameworks and APIs that any third-party iOS developer can already work with. They’re leveraging EventKit for reminder/calendar event retrieval and creation; they’re using MapKit to load inline snippets of Apple Maps locations; they’re using Mail’s native compose sheet and Safari View Controller to let users send pre-filled emails or browse webpages manually; they’re integrating with MusicKit to play songs from Apple Music, provided that you have the Music app installed and an active subscription. Theoretically, there is nothing stopping Perplexity from rolling additional frameworks such as ShazamKit, Image Playground, WeatherKit, the clipboard, or even photo library access into their voice assistant. Perplexity hasn’t found a “loophole” to replicate Siri functionalities; they were just the first major AI company to do so.

It’s been a few months since Perplexity rolled out their iOS assistant, and, so far, the company has chosen to keep the iOS integrations exclusive to voice mode; you can’t have text conversations with Perplexity on iPhone and iPad and ask it to look at your reminders or calendar events.

Anthropic, however, has done it and has become – to the best of my knowledge – the second major AI lab to plug directly into Apple’s native iOS and iPadOS frameworks, with an important twist: in the latest version of Claude, you can have text conversations and tell the model to look into your Reminders database or Calendar app without having to use voice mode.

Read more

I Have Many Questions About Apple’s Updated Foundation Models and the (Great) ‘Use Model’ Action in Shortcuts

Apple's 'Use Model' action in Shortcuts.

Apple’s ‘Use Model’ action in Shortcuts.

I mentioned this on AppStories during the week of WWDC: I think Apple’s new ‘Use Model’ action in Shortcuts for iOS/iPadOS/macOS 26, which lets you prompt either the local or cloud-based Apple Foundation models, is Apple Intelligence’s best and most exciting new feature for power users this year. This blog post is a way for me to better explain why as well as publicly investigate some aspects of the updated Foundation models that I don’t fully understand yet.

Read more

Testing DeepSeek R1-0528 on the M3 Ultra Mac Studio and Installing Local GGUF Models with Ollama on macOS

DeepSeek released an updated version of their popular R1 reasoning model (version 0528) with – according to the company – increased benchmark performance, reduced hallucinations, and native support for function calling and JSON output. Early tests from Artificial Analysis report a nice bump in performance, putting it behind OpenAI’s o3 and o4-mini-high in their Intelligence Index benchmarks. The model is available in the official DeepSeek API, and open weights have been distributed on Hugging Face. I downloaded different quantized versions of the full model on my M3 Ultra Mac Studio, and here are some notes on how it went.

Read more

Shareshot 1.3: Greater Image Flexibility, New Backgrounds, and Extended Shortcuts Support

If you have a screenshot you need to frame, Shareshot is one of your best bets. That’s because it makes it so hard to create an image that looks bad. The app, which is available for the iPhone, iPad, Mac, and Vision Pro, has a lot of options for tweaking the appearance of your framed screenshot, so your final image won’t have a cookie-cutter look. However, there are also just enough constraints to prevent you from creating something truly awful.

You can check out my original review and coverage on Club MacStories for the details on version 1.0 and subsequent releases, but today’s focus is on version 1.3, which covers three areas:

  • Increased image size flexibility
  • New backgrounds
  • Updated and extended Shortcuts actions
Adjusting sizes.

Adjusting sizes.

With version 1.3, Shareshot now lets you pick any output size you’d like. The app then frames your screenshot and fits it in the image size you specify. If you’re doing design work, getting the exact-size image you want out of the app is a big win because it means you won’t need to make adjustments later that could impair its fidelity.

A related change is the ability to specify a fixed width for the image that Shareshot outputs. That means you can pick the aspect ratio you want, such as square or 16:9, then specify a fixed width, and Shareshot will take care of automatically adjusting the height of the image to preserve the aspect ratio you chose. This feature is perfect if you publish to the web and the tools you use are optimized for a certain image width. Using anything wider just means you’re hosting a file that’s bigger than necessary, potentially slowing down your website and resulting in unnecessary bandwidth costs.

Shareshot is stripey now.

Shareshot is stripey now.

Shareshot has two new categories of backgrounds too: Solidarity and Stripes. Solidarity has two options styled after the Ukrainian and Palestinian flags, and Stripes includes designs based on LGBTQ+ colors and other color combinations in a variety of styles. All of the new categories allow you to adjust several parameters including the angle, color, saturation, brightness, and blur of the stripes.

Examples of angles.

Examples of angles.

Finally, Shareshot has revamped its Shortcuts actions to take advantage of App Intents, giving users control over more parameters of images generated using Shortcuts and preparing the app for Apple’s promised Smart Siri in the future. The changes add:

  • Support for outputting custom-sized images,
  • A scale option for fixed-width and custom-sized images, and
  • New parameters for angling and blurring backgrounds.

The progress Shareshot has made since version 1.0 is impressive. The app has grown substantially to offer a much wider set of backgrounds, options, and flexibility without compromising its excellent design, which garnered it a MacStories Selects Award last year. I’m still eager to see multiple screenshot support added, a feature I know is on the roadmap, but that’s more a wish than a complaint; Shareshot is a fantastic app that just keeps getting better.

Shareshot 1.3 is free to download on the App Store. Some of its features require a $1.99/month or $14.99/year subscription.