iiinova — where your digital self keeps evolving

Dave Guarino @allafarce.bsky.social · 12/02/2026

People are wondering when AI will be helping people navigate government services. The answer is, uh, right now. Here's Gemini (built into Chrome!) giving both accurate and helpful information to a common and high stakes question on a SNAP application.

183

Dave Guarino @allafarce.bsky.social · 10/02/2026

I really don’t like snark and try to minimize it in my life these days. But… Google’s model doing bad things it’s aware are bad in pursuit of maxing out KPIs is… pretty darn funny to me. (Also this paper scares me, as does much research in this area honestly.)

271

Dave Guarino @allafarce.bsky.social · 04/02/2026

If you have a persistent AI agent with memory, I highly recommend assigning it to read James C. Scott's classic, "Seeing Like A State"

190

Dave Guarino @allafarce.bsky.social · 01/02/2026

I built a little web app that makes it simple to send a photo postcard to friends/family (and the outbound card has a QR code that makes it easy for them to reply with their own photo postcard back) Such a delight. Seriously, use Claude Code to build stuff you want to exist in the world.

1103

Dave Guarino @allafarce.bsky.social · 31/01/2026

The most *practical* value I've gotten out of Claude Code is writing a bunch of helper scripts for Asana (where I manage my life + our household stuff). It's mostly grinding out friction, but for tasks I do hundreds of times a day... awesome. (And I usually run on Claude iOS app; no server needed)

020

Dave Guarino @allafarce.bsky.social · 30/01/2026

File under things that are wild to me: Claude Code can't access congress.gov pages because their Cloudflare config blocks all bot traffic.

0113

Dave Guarino @allafarce.bsky.social · 29/01/2026

Pretty sure today marks the first time a current or former Medicaid Director has ever used Claude Code. (Was pretty darn cool to facilitate it.)

150

Dave Guarino @allafarce.bsky.social · 26/01/2026

Candidly I can't believe Google continues to fumble its user advantage on AI so badly. Gemini in Google Docs... can't directly change formatting in the doc? (This is could be an interesting eval to track just how far behind Google's inertia is putting it.)

120

Dave Guarino @allafarce.bsky.social · 26/01/2026

I'm early in the exploratory phase, but it's so interesting to give Claude Code a SNAP automation project scope that is illegal under federal rules (but not implausible) and see it refuse to build it. (Interestingly, if asked to move barely >30 day apps to the end of the queue, it accepts.)

030

Dave Guarino @allafarce.bsky.social · 08/01/2026

Okay I do think my favorite use of a language model at this point is building a pipeline for Claude to ingest a recipe photo from a cookbook and unpack all the tacit cooking knowledge into explicit knowledge I can actually act on!

2100

Dave Guarino @allafarce.bsky.social · 07/01/2026

I built a Skill to access SNAP's federal regulations in AI agents as part of some bigger work. It was really enjoyable to see how easy this has become. (I'll confess to getting a bit turned around in the Claude docs on skills vs. commands vs. plugins)

070

Dave Guarino @allafarce.bsky.social · 05/01/2026

I've been wanting to try the Claude Agent SDK more directly and ended up building a tool that ingests recipes (from cookbook photo) and does a bunch of things, but the best one being making implicit aspects of the recipe explicit.

170

Dave Guarino @allafarce.bsky.social · 01/01/2026

Using Claude Code I built a tiny little Apple Watch app to talk to… Claude! (via Siri) It’s called Norbert (cybernetics!) and has been super helpful for on the go tiny quick questions and staying off my phone. Getting it in TestFlight, DM me your email if you want to try it!

031

Dave Guarino @allafarce.bsky.social · 30/12/2025

I’ve now got Claude Code in the iPhone app running Python scripts under the hood to access our household management stuff in Asana and help me go through stuff on the go.

060

Dave Guarino @allafarce.bsky.social · 24/12/2025

Yet another helpful use for Claude Code: connect it to our household tracker (Asana) and go through open items and propose what an actionable, concrete next step is.

260

Dave Guarino @allafarce.bsky.social · 17/12/2025

The other night I spiked a little "Abundance Legislative Linter" to read through proposed city ordinances (for now, SF) and do some basic evaluation on how well or poorly they align to "abundance" principles. Claude Code enables so many fun side projects.

020

Dave Guarino @allafarce.bsky.social · 28/11/2025

Step 1: ask Claude for stretch suggestions Step 2: have nano banana generate an illustration of the stretch

210

Dave Guarino @allafarce.bsky.social · 18/11/2025

Google Gemini 3 Pro is out today. I ran through my standard "hard SNAP question" which I use to eval new models and it... absolutely excels. (If you've got a hard public policy/benefits question you want to test, leave a comment and I'll run it through as I have time.)

090

Dave Guarino @allafarce.bsky.social · 29/10/2025

My company, Propel, is doing a direct cash transfer to some high need SNAP families given November deposits are indefinitely delayed due to the shutdown. Propel is contributing $1 million in company funds and looking to raise another $9m from partners. www.propel.app/shutdown-fun...

094

Dave Guarino @allafarce.bsky.social · 13/09/2025

More progress on using Claude Code for my absolutely-personally-tailored daily todo list tool. First bit was lots of keyboard shortcuts a la vim. Next I want a voice interface (via Apple Watch) so I've prototyped that with a text-based chat interface that will eventually be driven by voice.

020

Dave Guarino @allafarce.bsky.social · 04/09/2025

I'm increasingly convinced Claude Code is an early glimpse of what general purpose AI with agency feels like. I'm experimenting with making it usable for non-programmers: - Created a custom output style called "non-technical user" - It explains what it's doing in lay terms

040

Dave Guarino @allafarce.bsky.social · 31/08/2025

I've been using a pattern I call "Claude Compadre" — using Claude Code, but for decidedly non-coding tasks. This approach means I can have Claude quickly "grow" its own capabilities via code generation. Example here: generating code to hit the Asana API to help me with family task planning

191

Dave Guarino @allafarce.bsky.social · 30/08/2025

It is time. Hello, Claude, my friend.

020

Dave Guarino @allafarce.bsky.social · 25/08/2025

Using Claude Code to check logs for suspicious activity

020

Dave Guarino @allafarce.bsky.social · 15/07/2025

In my newsletter today I sketched out my own AI moonshot, a hyper niche one: Can we use today’s AI coding capabilities not for greenfield app code generation, but rather for automated characterization test coverage on large legacy systems we’re afraid of changing?

130

Dave Guarino @allafarce.bsky.social · 14/07/2025

A moment of appreciation for my morning walk.

0121

Dave Guarino @allafarce.bsky.social · 12/07/2025

I need a political scientist to look into this, stat

2120

Dave Guarino @allafarce.bsky.social · 08/07/2025

You can just… learn to cook. (Sautéed zucchini with salt, pepper, olive oil, lemon juice, chili flakes, mint, cilantro)

090

Dave Guarino @allafarce.bsky.social · 12/06/2025

Underneath this sign lies a rich and hilarious story of a no good, very bad afternoon someone had.

092

Dave Guarino @allafarce.bsky.social · 27/04/2025

Me when I pick up the Zuni Cafe cookbook and read that they salt their chicken TWO TO THREE DAYS ahead of cooking time:

670

Dave Guarino @allafarce.bsky.social · 23/04/2025

We evaluated a number of different models (OpenAI models, Anthropic Claude Sonnet versions, and 2 versions of Google Gemini) and saw some initial front running by the Gemini models. (Note, this is very much an illustrative starting eval, not comprehensive!) (3/n)

130

Dave Guarino @allafarce.bsky.social · 22/04/2025

Using AI to iteratively generate abstract representations of James C. Scott's "Seeing Like A State"; I rather like this one (DALLE)

030

Dave Guarino @allafarce.bsky.social · 26/03/2025

I don't post pictures of our daughter here, but I'll make an exception for this one. (She is a literal bundle of joy.)

1100

Dave Guarino @allafarce.bsky.social · 23/03/2025

Another lens on language models is that they are an incredibly capable ETL engine for semantics. Here: transform a recipe into mise en place steps

170

Dave Guarino @allafarce.bsky.social · 02/03/2025

One of the less common situations where Claude failed me. Luckily Gemini worked like a charm. Scan Costco receipt, grab the prices for select items, sum, divide by 2 (Unsurprisingly this is splitting our Costco run)

140

Dave Guarino @allafarce.bsky.social · 02/03/2025

Oh nice. I've been trying to go in that direction more, though I usually have farro standalone in a batch for the week then do a light garlic sautee w/ salt/pepper/EVOO/lemon juice. FWIW this bean recipe changed my bean game entirely. Far better than standard approach IMO.

110

Dave Guarino @allafarce.bsky.social · 13/02/2025

I appreciate Marina speaking very openly about what a lot of us have felt (absolutely including myself) reason.com/2025/02/13/i-tried-to-fi…

161

Dave Guarino @allafarce.bsky.social · 10/02/2025

Maybe I really should start a “Cooking with Claude” blog or something. I’ve never browned butter (doing sage) and so I… just show it pictures and let it tell me if it’s browned yet.

020

Dave Guarino @allafarce.bsky.social · 01/02/2025

I earnestly believe one of the best ways to assess AI models is to use them to augment your cooking. Why? - Low risk - Can add value at almost any level of cooking ability - If you know cooking well, you can see where it does well or falls down (and how specifically) I use Claude daily for this.

0130

Dave Guarino @allafarce.bsky.social · 04/01/2025

The more random things I test using AI for, the more I feel it...

191

Dave Guarino @allafarce.bsky.social · 04/01/2025

Google Gemini Deep Research, first go of it! And it... just rejects my prompt. Well then. (It must have had to do with the mention of government safety net benefits / SNAP / Medicaid, but, boy, is that an aggressive safety filter.)

020

Dave Guarino @allafarce.bsky.social · 03/01/2025

Claude: "I actually diverge from pure GTD here..." Me: "Can you say more about how you developed that perspective?" (I really enjoyed this exchange — and it's gesturing towards *something* interesting more generally.)

040

Dave Guarino @allafarce.bsky.social · 30/12/2024

Still perhaps my favorite diagram ever (from Venkatesh Rao's Ribbonfarm post, "How to Fall Off the Wagon")

172

Dave Guarino @allafarce.bsky.social · 28/12/2024

Example of a very practical conversation with Claude that has helped me (it continues on, but this will give you a sense); this one related to a nutrition and food prep issue.

110

Dave Guarino @allafarce.bsky.social · 26/12/2024

A small but incredibly useful application of LLMs for me: - Use the Superwhisper app to take verbal notes on the go - Add a custom prompt to make it into bullets - Now can use "Share" easily to Obsidian as outline bullet

030

Dave Guarino @allafarce.bsky.social · 13/12/2024

I wish these critiques were more “scientific inference is possible with a variety of methods beyond quant data” but instead they tend to be:

191