s_brady

A runtime for a long-lived LLM agent with ambient continuous self-perception, persistent memory, defined authority, domain-specific autonomy, and forensic accountability, all in a long ongoing relationship with a human. I call this type of system an Artificial Retainer, a non-human cross between a guide dog and someone like your accountant or lawyer. It is not designed to be your friend, but it could be a valuable colleague. Think of this as an attempt to build a trusted stable agent with a stable character that could last decades.

https://github.com/seamus-brady/springdrift

https://arxiv.org/abs/2604.04660

Inspired by [1] I have been working on a system to integrate the Normative Calculus of Lawrence Becker from "A New Stoicism" [2] into an LLM agent. This works out kind of like Constitutional AI but prompt engineering based. There is a Raku and a Python implementation. I much preferred using Raku as the built in text handling and multithreading is a joy to work with. Python is very clunky compared to it. it just has better libraries.

I make no great claims for the system, it has major issues being prompt based. It is a prototype to explore the feasibility of the idea of giving a chatbot arete, a code of conduct. There are few tests, no evals so all the usual caveats! An intellectual exercise in possibilities not currently being explored anywhere else. Does it work? Hmm, almost :)

It extracts normative propositions from incoming user requests then compares then to it's own internal ethical normative propositions using the Normative Calculus. The system also uses the Decision Paradigm algorithm from Lee Roy Beach [3] to make a forecast on whether to take up the user's task or not.

[1] https://link.springer.com/article/10.1023/A:1013805017161 [2] https://www.jstor.org/stable/j.ctt1pd2k82 [3] https://books.google.ie/books/about/The_Psychology_of_Narrat...

I might try to arrange that :) Thanks for the interest!

I am working on an agent cognitive architecture based around LLMs. Been working on it for a while. The main difference from all the dozens out of agentic systems out there is that has been designed so that it can introspect fully and it has a machine ethics layer based on the work a modern Stoic philosopher. I am trying to build a system that I would like to exist.

100 years from now BitCoin will be seen for what it really is - the computing icing on top of the large excrement cake that is our industrial civilisation.

I really want to like Rust, I like the intention of what the language is trying to do. But in a universe where languages like Smalltalk, Eiffel and Lisp exist, it just feels like a step backwards. Surely the computer should be doing the heavy lifting? What happened to my bicycle for the mind? Just my opinion. I admire the work going on in Rust but the complexity makes me sad.

Also see the code repository at https://github.com/romasch/scoop_patterns

I always use gandi.net for searching for domains. They are honest brokers. Never had an issue.

Your comment is interesting but seems to conflate two separate though related areas. The need for a body arises from the embodied cognition school of AI which suggests that intelligence is fundamentally embodied, hence the need for a robot equivalent to a body for truly understanding language.

However this does not necessarily have to be related to causality, and counterfactual statements about a causal model. The math behind counterfactuals and causality is actually well understood now (see any of Pearl's books). It does not actually require that a system be embodied, just that the system have some suitable (and correct) causal model of the world.

It would of course be amazing to have both in one system, but that is not required. An AI system that understood causality and language could be bootstrapped from causal models supplied by humans - or even other AIs :)

I am almost tempted to add this.

Hi - Mousemacs author here.

There is a way to pick and choose :)

The context menu in Mousemacs is a couple of dozen lines of Elisp and would be simple to rewrite. You can simply create your own context menus.