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

I feel like people downplay that the major determinants of things happening in the world are: - They are possible (eg technologically) - They have a payout structure Example: many forms of fraud meet 1, but not 2, and so generally don’t happen.

New post: Building a real-time state update pipeline for 370,000 SNAP recipients with AI open.substack.com/pub/daveguar...

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.)

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...

One awesome use of LLMs I've enjoyed is giving them a bunch of technical docs for a tool, and turning it into an audio-friendly text doc, which then I listen to with ElevenLabs Reader. Here's an example, on Claude Skills claude.ai/public/artif...

“The AWS outage is affecting our daycare” is not something I expected to say.

Finished Dune. Worth continuing on to Messiah?

Yet another use of Claude Code I probably won’t go back from: Working with an API I don’t know, just tell it to comprehensively read the docs and come up with some options for me (Solved a very annoying subtle bad default for me last week)

We need to start talking about what an AI jobs displacement benefit program would actually look like.

An essay I'm simmering on — thinking about government's use of tech (& AI), disambiguating problems of: - Capability - Alignment - Dysregulation (cc @dsquareddigest.bsky.social) An important differential diagnosis for interventions! And one that I think is implicit (and/or wrong) too often.

New research post! We tested ~45 AI models released over the past 18 months on a hard SNAP policy question (one with a meaningful potential harm profile.) We saw *dramatic* improvements in how they handled policy complexity. www.propel.app/insights/how...

One meta thing with governance of gov use of AI I feel the traditional policy world is ignoring a bit is that the AI capabilities at the frontier actually can be a huge tool in doing oversight, monitoring, etc. scaling accountability

Kernels 02: Claude Compadre (Claude Code for non-coding things) open.substack.com/pub/daveguar...

Having my newsletter emails say "Dave Guarino from Dave Guarino's Occasional Newsletter" has annoyed me long enough. So I hereby announce my newsletter's new name: "Plausible Legibility"

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.

I've been picking at an idea, that a corollary to "idea machines" in certain problem spaces is the creation of "agency machines" In domains with high stuckedness, sometimes you need to inject a new actor with lots of ability (and incentive) to do things

I did it. I waited out the need to actually learn the Javascript ecosystem. Enjoying this AI coding future EVEN MORE upon this realization.

wrote my own static site LLM client in a few hours that does exactly what I want and nothing more. gpt-5, claude sonnet and opus, gemini 2.5 pro + web search + reasoning toggle. it rules. will make repo public soon

I'm using Claude Code to add vim-style keyboard interactions to a personal todo app because THE COST OF PERSONALLY TAILORED SOFTWARE HAS BECOME $20 PER MONTH.

I’m beginning to suspect one of the highest societal value things to do right now given AI is to make the work displacement effects it will have (is having…) legible and indisputable.

I will go out on a limb and say that I do believe we should use new AI capabilities to increase the capacity of the state to deliver on the goals democratic governance processes have arrived at.

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

I went to Berkeley so long ago that in my day effective altruism was just called “applied econometrics”

Started reading the Expanse series (Leviathan Wakes) and really enjoying it, particularly the political economy dimensions!

I'm going to write up my Claude Compadre™ thing (using Claude Code for non-coding things) but a few tips: 1. Have it take notes in local Markdown files, and self-update Claude.md based on what it learns 2. Use Opus 4.1 for the initial planning (can pay per token by API just for this with /login)

Me: "Man, these Claude usage limits can be a bummer! Opus is so much better!" Also me: "Write a satirical dialogue in the style of Armando Ianucci about Krushchev's visit to a US supermarket. Think ultrahard."

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

Somewhat strangely, I'm finding the Asana MCP server does not work well, whereas when I just use the model to generate code that directly hits the Asana API it works fine. Seems like a design/implementation gaffe?

It is time. Hello, Claude, my friend.

Claude Opus 4.1, to me, while building out a comprehensive policy understanding of SNAP simplified reporting: “The confusion in the documents shows how complex this system is - if we're getting tripped up just researching it, imagine how confusing it must be for actual SNAP recipients!“ EXACTLY

Using Claude Code to check logs for suspicious activity

I think using AI as a cooking assistant would get a lot more people seeing the value these odd alien intelligences present in their current form.

Final judgment on Piranesi: second half much more enjoyable, but, to me, the reveal was not worth the slog.

Piranesi better have one hell of a punchline for how much it’s dragging.

Wow, using an AI transcription tool like Wispr Flow (which is what I use to brain dump ideas) might be the biggest breakthrough in my writing process. It just makes getting started so much easier.

One of my favorite nouns in public benefits land is "EDG" I've heard more than once the "should we call people users? people" households? case? or..." An "EDG" is: Eligibility Determination Group

File under "good uses of AI": optimizing meals for balance and health I took my base preferred breakfast (high protein yogurt) and used AI to make it really well balanced (adding ground flaxseed and hemp hearts, in addition to berries and nuts)

Enjoyed this by @allafarce.bsky.social open.substack.com/pub/daveguar...

I do have to give it to Gen Z for Turnstile.

We tackled some of this in the Data Rights Protocol work I consulted on for Consumer Reports. IMO there are already legal frameworks for people to delegate certain tasks (such as filing DSARs) to companies acting as agents on their behalf, and this isn't much different if LLMs are added to the mix

We really need to start having the policy framework conversation around AI agent access to online government services. This is going to happen no matter what. Not having even a basic policy scaffolding that sets norms will create a selection effect for less good actors.

Excellent bumper sticker.

You definitely know I occupy a very specific niche when I say to a co-worker, "The U.S. is in a down round on the safety net."

Deeply enjoyed Claude Code chastizing my colleague for having the local version of an alpha app talking to the production database. (It was fine, but also funny to see Claude panicking about it.)

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?

A moment of appreciation for my morning walk.

A perhaps heterodox view in my world: I don't think the 50 states building roughly the same system is a meaningful problem when the programs are administered at that state level. In fact, if anything, AI increases the possibility of getting those systems more contextually right.

I need a political scientist to look into this, stat

The most shocking thing of getting even semi-decent at mindfulness meditation is realizing just how damn anxious I have normally been in many contexts! At the airport and being able to notice it come up is astounding!