719 karma · joined October 20, 2013
1. My agents do not take direct action, they run programs.
2. Programs are not LLM hits/real-time output; they don't MAX tokens the MAX determinism.
3. Programs are logistical wrappers for Protocols where the guardrails are (RLVR.ai)
4. Policies for generating programs are democratically governed re: fec.dev - they get voted on
5. Elected-HITL implements the policy pipelines and ontological abstract intents [and their maps]
I would be really interested to learn about the Gov. models that others are using but this seems to be something that linked0-in (which i loathe) discusses (in the most pedestrian/luddite) terms more than HN.
Even in the cases where the answer is "yes"; I believe that working backwards from the why could provide a more elegant path to accomplishing said goal.
Aside from "PG's blog" this is a community. People wish each other happy holidays, offer support to one another, challenge each other etc... In that sense it transcends both PG and YC. The internet is not what it used to be but HN is a real community to me and I am truly grateful for that. As such, I would like to make an effort to meet more people and hang out in real life.
re: https://www.npr.org/2026/08/22/nx-s1-5931446/flock-fallout-c...
Travel is such a huge play here because its inherently social; so "^n viral loop where N is travelers; odds are most will have some meta app so possibly lower friction here too. Not to mention the adjacent travel econ: e.g.: eat, sleep etc..
Amplified an order of magnitude for the e-mail piece given how badly Meta would like to have google's g-mail data.
Either way, interesting play IMO.
Note: Moved from dupe thread.
Travel is such a huge play here because its inherently social; so "^n viral loop where N is travelers; odds are most will have some meta app so possibly lower friction here too.
Amplified an order of magnitude for the e-mail piece given how badly Meta would like to have google's g-mail data.
Either way, interesting play IMO.
I disagree, I think YC is fully to blame here as are the other grifters of the current administration.
I apologize for not being clearer in my comment. I actually agree with your response and fully understand that there is a fundamental difference but also believe that the outcomes of both the aforementioned are aligned.
re: https://time.com/article/2026/08/13/trump-sued-truth-social-...
1. Alister Martin is a real physician and that seat is a seeded placeholder using a real person's name, adding AI-native and customizing weights based on a corpus does not in any way account for the "human element here. I did not consider this.
2. Crisis handling. Human handoff only. I have actually had a few successes here https://erpo.law/
3. The site doesn't explain itself. THIS THIS THIS. I have been working on this all day. I am just a dev and 99% of my users are people i talk to, ask, walk through etc. some touch point with me and I think that may have impacted feedback in a way I did not understand until today.
4. "Thousands" of programs is 212. - Its like 70k and only like 204 have ever been completed.
Two things: 1: This isn't a HIPAA covered entity today, but the back-end API services just work with OpenEMR services blah blah...but your underlying point stands. 2: Im not sure where you saw hard coded secrets; sync didn't find anything, I looked manually and I didn't either but if you do please email me and any other vulnerable party on the same thread so that the issue can be handled ASAP.
At times like this I like to think that I'd rather be better than right, so I will take a serious look at how to improve here.
Edit: 1 more, the agents done "make decisions" in the way I think you mean. Its more like an attempt at MAXING the deterministic element of the workflows: https://wiki.project20x.com/
I would like to provide some explanation -
0. In prison you cannot always type things on your tablet. Often, we preferred phone / voice interfaces. I am correcting this now; defaulting to text input.
1. My pops was a social service worker for 30 years; he would always explain to me all the repetitive stuff that people had to deal with and how it hurt them so this: "Codify" is meant to be automated workflows that mitigate that barrier. Codification seemed like the best way to do that; I still believe this and its not domain specific, speaking to lack of problem understanding. The agent leads people through the "codified" workflows (aka: Programs).
2. I have no tokens, budget or other; I setup my own local coding ENV so maybe change textbooks, LOL (kidding ofcorse; glut of tokens = AI slop i get it).
3. What am I even looking at??? - When you enter things like "I think I have COVID" into ChatGPT etc.. you get a wall of text that people don't want to read. When people go here https://www.nyc.gov/site/doh/covid/covid-19-main.page - same thing. What you are looking at is my attempt to turn these walls of text into real automated workflows that have agents and HITL's guide them from an intent to an outcome. I obviously am not doing that good a job ATM but 2k+m users have completed their programs w/ verified outcomes but thats less than 15% of the programs initiated so your feedback is extremely welcomed and appreciated.
Edit: In terms of AI/LLM's etc..
> This hit me hard, I have been thinking about this a lot lately. I'm not sure it's what makes "us human" its what makes humans (us) better than other species. It was intelligence, this was used to create distinction between us and other living beings, different races etc... Now its kind of gone; in some ways. Loss of meaning, purpose, place etc... The one thing we used as a ranking metric is now a commodity, so....? I don't even know how to finish that. So why care, why work...shit just why? Capitalism makes it even worse because we are judged based on what we output, does that even make sense anymore? I think the article is confusing because the "state: is confusing; to me at least.
.... 3 responses ....
> Thats totally fair, and TBH - I am also very concerned for my wellbeing as well; I and many others are not doing so well because, in my case I no longer see this "vapid" state of existence as ephermial. I have been reading more and more; I guess looking ot knowledge as some eort of ends vs a means to an end for once. Camus, Stokely Carmichael (Kwame Ture), Dostoevsky's underground man etc...
Camus: The universe was always going to stay silent when you demand meaning from it; the answer isn't a better metric, it's to push the rock anyway ("imagine Sisyphus happy").
Dostoevsky [underground man]: Refusing to be a piano key in someone's optimized Crystal Palace
Stokely Carmichael: "Racism is not a question of attitude, it's a question of power. Racism gets its power from capitalism."
My conclusion: AI didn't take our meaning, It made me realize I have always been looking in the wrong place and thus reacting ignoratly when I felt "denied" this thing I feel entitled to.
Love.
Edit: Love; paradoxically, ive felt both entitled to and unworthy of so I'm not sure WTF to do with that.
To wit: Our love of self is so closely tied to our output and if we have no output do we have value?
Edit: tl;dr - I am not sure I understand the point of anything anymore and many others feel the same way. I do not think this is some "existential crisis" I believe it is a logical conclusion to draw given the evidence presented by the day and age we live in.
I have been reading more and more; I guess looking ot knowledge as some eort of ends vs a means to an end for once. Camus, Stokely Carmichael (Kwame Ture), Dostoevsky's underground man etc...
Camus: The universe was always going to stay silent when you demand meaning from it; the answer isn't a better metric, it's to push the rock anyway ("imagine Sisyphus happy").
Dostoevsky [underground man]: Refusing to be a piano key in someone's optimized Crystal Palace
Stokely Carmichael: "Racism is not a question of attitude, it's a question of power. Racism gets its power from capitalism."
My conclusion: AI didn't take our meaning, It made me realize I have always been looking in the wrong place and thus reacting ignoratly when I felt "denied" this thing I feel entitled to.
Love.
Edit: Love; paradoxically, ive felt both entitled to and unworthy of so I'm not sure WTF to do with that.
Edit: I am not in anyway trying to be obtuse or reductive, I simply want to understand your statement. Apologies if it comes across that way.
This is really great feedback man; and I am literally going to fix these things right now.
1. I am going to open up all the programs so users can click through all of the steps and really understand, like a preview.
2. I am going to just use my horrible writing skills and do the copy myself. I am very insecure about my writing so I leaned on AI for that probably way too much.
3. I am going to add a video NOT of program/protocols but of the actual process that its automating; e.g.: https://wiki.codify.nyc/agent/posts/nyc-311-apply-victim-com... and some of the user testimonials; for example - the core use case is care plan automation. 1k of the 2k users I was speaking about all were from crohns.ai
I think I not only missed the mark here but did the exact opposite of what I wanted to. Codification is supposed to simplify complex workflows and it seems like I did the opposite here and I can totally see how nobody would ever be able to tell that I am automating a process here.
The amount of embarrassment you just saved me I cannot thank you enough for. I was about to do my first "email/blast" style marketing campaign but I am going to dig into this first. If you don't mind, I would like to email you when I made the fixes.
Edit: The thing I don't know how to express is that the page you like, that can take a lot of work. I want to automated all of the things possible so that instead of reading a page its essentially just a program and the agent guides you (for real) through everything required to complete whatever process or flow the page describes.
1. A user would start at https://dohmh.codify.nyc and say and say whatever their intent is, e.g.: "I think I got food poisoning" or "I think I have COVID" etc...
2. The system would then either find a program for that intent or help the user make a protocol to reach their desired outcome (for that intent).
3. The program is a set of modules like: Assessments, Followups, Services etc... and the user is guided through each of them in an automated fashon. HITL is there when needed but the agent is the primary guide.
The whole point is that lots of processes just break down to a series of steps and deterministic logic that can be "codified". Thats why I call it "Codify".
I have had about 2000 programs completed but thats only 15% of the programs that users have started; so I think you may be right. I really need to improve my messaging.
One another note, I genuinely would like to thank you for the feedback. Critical feedback is hard to hear many time but its by far the most useful. I in no way meant to spam the comments but I don't otherwise know how to execute on the "tell people" part of "Do things, tell people".
I took all of these https://www.nyc.gov/site/doh/health/health-topics.page and turned them into guided protocols, staffed w/ the required agents and HITL.
Here are the "Programs" - https://dohmh.codify.nyc/programs
example protocol: https://dohmh.codify.nyc/protocol/71776
I was hoping it would be enough to stand out and get an interview w/ the "PIT Crew" but no such luck, reach out if you want to chat or hack on some NYC/Civic stuff.