Dave Guarino
@allafarce.bsky.social
Software and complex (not complicated) systems. Pursuing the public good, sometimes with technology.
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.
- 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.
November 23, 2025 at 5:13 PM
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.
- 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...
Building a real-time state update pipeline for 370,000 SNAP recipients with AI
This is a crosspost of a write-up I did on the Propel blog about how we implemented a pipeline of monitoring the 50 state SNAP agencies’ websites for updates on the government shutdown, and piped it o...
open.substack.com
November 19, 2025 at 7:22 PM
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.)
(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.)
November 18, 2025 at 5:39 PM
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.)
(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...
Propel is contributing $1 million in company funds and looking to raise another $9m from partners.
www.propel.app/shutdown-fun...
October 29, 2025 at 5:26 PM
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...
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...
Here's an example, on Claude Skills claude.ai/public/artif...
claude_skills_audio_guide.md | Claude
Comprehensive technical guide to Anthropic's Claude Skills system - architecture, implementation, best practices, and real-world applications for AI agents.
claude.ai
October 25, 2025 at 7:02 PM
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...
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.
October 20, 2025 at 6:25 PM
“The AWS outage is affecting our daycare” is not something I expected to say.
Finished Dune. Worth continuing on to Messiah?
October 19, 2025 at 12:45 AM
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)
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)
October 5, 2025 at 10:42 PM
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)
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.
We need to start talking about an AI benefit design
And more specifically: how we design it to actually work
open.substack.com
October 1, 2025 at 3:55 PM
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.
- 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.
September 19, 2025 at 6:54 PM
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.
- 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...
www.propel.app/insights/how...
AI Models Are Getting Dramatically Better at Complex Policy Questions: Evidence from SNAP Asset Limits
Testing 45 AI models on SNAP eligibility questions reveals dramatic improvements. See how GPT, Claude, and Gemini evolved from harmful to helpful answers.
www.propel.app
September 17, 2025 at 6:27 PM
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...
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
September 16, 2025 at 4:16 PM
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...
open.substack.com/pub/daveguar...
Kernels 02: Claude Compadre (Claude Code for non-coding things)
Also: is curiosity all you need?
open.substack.com
September 16, 2025 at 2:41 PM
Kernels 02: Claude Compadre (Claude Code for non-coding things)
open.substack.com/pub/daveguar...
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"
So I hereby announce my newsletter's new name:
"Plausible Legibility"
September 15, 2025 at 4:00 AM
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"
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.
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.
September 13, 2025 at 3:53 AM
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.
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
In domains with high stuckedness, sometimes you need to inject a new actor with lots of ability (and incentive) to do things
September 8, 2025 at 11:08 PM
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
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.
I waited out the need to actually learn the Javascript ecosystem.
Enjoying this AI coding future EVEN MORE upon this realization.
September 7, 2025 at 6:06 PM
I did it.
I waited out the need to actually learn the Javascript ecosystem.
Enjoying this AI coding future EVEN MORE upon this realization.
I waited out the need to actually learn the Javascript ecosystem.
Enjoying this AI coding future EVEN MORE upon this realization.
Reposted by Dave Guarino
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
August 31, 2025 at 1:49 PM
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.
September 7, 2025 at 2:43 AM
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.
September 6, 2025 at 8:47 PM
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.
September 4, 2025 at 1:16 AM
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'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
September 3, 2025 at 11:31 PM
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'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”
September 3, 2025 at 5:04 PM
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!
September 2, 2025 at 9:45 PM
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)
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)
September 2, 2025 at 3:21 AM
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)
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)