Tyler Lifke

Healthcare AI Specialist

[Andrej Karpathy @karpathy]

Very interested in what the coming era of highly bespoke software might look like.

Example from this morning - I've become a bit loosy goosy with my cardio recently so I decided to do a more srs, regimented experiment to try to lower my Resting Heart Rate from 50 -> 45, over experiment duration of 8 weeks. The primary way to do this is to aspire to a certain sum total minute goals in Zone 2 cardio and 1 HIIT/week.

1 hour later I vibe coded this super custom dashboard for this very specific experiment that shows me how I'm tracking. Claude had to reverse engineer the Woodway treadmill cloud API to pull raw data, process, filter, debug it and create a web UI frontend to track the experiment. It wasn't a fully smooth experience and I had to notice and ask to fix bugs e.g. it screwed up metric vs. imperial system units and it screwed up on the calendar matching up days to dates etc.

But I still feel like the overall direction is clear:
1) There will never be (and shouldn't be) a specific app on the app store for this kind of thing. I shouldn't have to look for, download and use some kind of a "Cardio experiment tracker", when this thing is ~300 lines of code that an LLM agent will give you in seconds. The idea of an "app store" of a long tail of discrete set of apps you choose from feels somehow wrong and outdated when LLM agents can improvise the app on the spot and just for you.
2) Second, the industry has to reconfigure into a set of services of sensors and actuators with agent native ergonomics. My Woodway treadmill is a sensor - it turns physical state into digital knowledge. It shouldn't maintain some human-readable frontend and my LLM agent shouldn't have to reverse engineer it, it should be an API/CLI easily usable by my agent. I'm a little bit disappointed (and my timelines are correspondingly slower) with how slowly this progression is happening in the industry overall. 99% of products/services still don't have an AI-native CLI yet. 99% of products/services maintain .html/.css docs like I won't immediately look for how to copy paste the whole thing to my agent to get something done. They give you a list of instructions on a webpage to open this or that url and click here or there to do a thing. In 2026. What am I a computer? You do it. Or have my agent do it.

So anyway today I am impressed that this random thing took 1 hour (it would have been ~10 hours 2 years ago). But what excites me more is thinking through how this really should have been 1 minute tops. What has to be in place so that it would be 1 minute? So that I could simply say "Hi can you help me track my cardio over the next 8 weeks", and after a very brief Q&A the app would be up. The AI would already have a lot personal context, it would gather the extra needed data, it would reference and search related skill libraries, and maintain all my little apps/automations.

TLDR the "app store" of a set of discrete apps that you choose from is an increasingly outdated concept all by itself. The future are services of AI-native sensors & actuators orchestrated via LLM glue into highly custom, ephemeral apps. It's just not here yet.

[Claude @claudeai]

Today we’re shipping 3 more updates for Claude Code:

- Claude Code on Android
- Hotkey model switcher
- Context window info in status lines

[Tyler Lifke @lifter_of_keys]

@alexalbert__ @zeddotdev @posit_pbc @marimo_ai That first one is pretty likely to come in an update soon. I ran out of time on the contest, but intend on updating this periodically, particularly if folks end up using it.

[Tyler Lifke @lifter_of_keys]

@alexalbert__ @zeddotdev @posit_pbc @marimo_ai Potential improvements:
- Embedded charts in ClaudeCodeR window
- Fully supported ACP with Gemini CLI and Github CLI integrations
- More R user-friendly UI. It's pretty barebones and lacks lots of Claude Code functionality like progress indicators, tab completion, file tagging

[Tyler Lifke @lifter_of_keys]

@alexalbert__ @zeddotdev @posit_pbc @marimo_ai @AnthropicAI @claudeai @alexalbert__ Hope I'm not too late for consideration for the contest!

[Tyler Lifke @lifter_of_keys]

@alexalbert__ @zeddotdev @posit_pbc @marimo_ai @posit_pbc @zeddotdev @AnthropicAI @claudeai An official collab would be fantastic for R users -- hope you enjoy my proof of concept!

[Simon Willison @simonw]

Vibe coding is irresponsibly building software through dice rolls, not caring what code is produced

What about when engineers at the top of their game use AI tools responsibly to accelerate their work?

I propose "vibe engineering"!

[Alex Albert @alexalbert__]

We’re running a “Built with Claude Sonnet 4.5” challenge.

We want to see the coolest things you can build with 4.5 in the next week.

Four winners will receive one year of Claude Max 20x and $1k in Claude API credits.

[cat @_catwu]

We just shipped a bunch of updates to Claude Code, making it a more capable agent than ever. And on top of it: it’s now powered by Claude Sonnet 4.5.

[Sean Strong @sean_t_strong]

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5.

Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

[Simon Willison @simonw]

Wrote up my initial impressions of the brand new Claude Sonnet 4.5 - I think it may live up to Anthropic's claims of being the "best coding model in the world", for the next few weeks at least!
https://t.co/NQlytA1Xlm

[Simon Willison @simonw]

I heard that Shopify and Cloudflare are both increasing their intern intake this year because an intern armed with AI tools can produce value a whole lot faster than interns in previous years

Any other companies doing this?

[Simon Willison @simonw]

Put together some notes on the new DeepMind paper "Video models are zero-shot learners and reasoners" - it makes a very convincing case that generative video models are to vision problems what LLMs were to NLP problems: single models that can solve a wide array of challenges

[Tyler Lifke @lifter_of_keys]

@LordOfRestocks Pretty dope, thanks for the tips!

[Tyler Lifke @lifter_of_keys]

@LordOfRestocks Anyone else out here in MN tryna snag a PS5?