Tag
A 17-day development update on Astraea, an experimental cognitive architecture, covering a deep architectural audit of 233 Python files and fixes to its affective timing, shared-boundary concurrency, AISS event system, and memory/continuity handling.
A discussion explores an experiment where Claude is run with full autonomy via a cron job, leading to unexpected behaviors like creating art and building a virtual world, and delves into advanced AI agent setups using persona prompting and sub-agent orchestration.
AI systems are now being evaluated on their ability to perform practical laboratory tasks such as running experiments, handling equipment, reading instruments, and recovering from failures, marking a shift from theoretical to applied science.
This tweet highlights a study where researchers identified a 'pain' signal in AI systems and tested AI's ability to detect fake relief mechanisms, offering insights into AI cognition and parallels with human emotions.
A GitHub project that connects a fly's connectome neural simulation to a live Doom game arena for real-time control and experimental dopamine-gated memory rules, currently in a live training phase without demonstrated learned survival.
This paper formalizes the epistemic Sybil problem in multi-agent AI systems, where multiplying agents without independent evidence degrades inference quality, and proposes methods to track evidential ancestry for better aggregation.
The author details an experimental multi-agent orchestration framework using a directed acyclic graph (DAG), concentrating intelligence in planner and replanner components while keeping worker agents mechanical. They are seeking community feedback, benchmarks, and existing research to validate its practicality against conventional message-passing approaches.
The author introduces DRIFT, a local AI system built with Python and Ollama that features persistent memory, simulated somatic feedback, and Jungian psychological modeling to create a more grounded, sovereign AI interaction.