Engineering Ideas
Subscribe
Sign in
Home
Notes
Archive
About
Tasklet is the "o1 moment" for long-horizon AI agents that learn on the job
A couple of weeks ago, Andrew Lee unveiled Tasklet, an AI agent with a two-tier design: a long-lived, high-level agent curates the system prompt…
Oct 27
4
1
Latest
Top
Discussions
The personal AI platform: technical blueprint
Pocketbase and LanceDB for extensible personal AI data plane and system of record
Sep 9
4
AI agency architecture-in-the-large: the relevant levels of abstraction
The "agent framework" level is just one among dozens of relevant architecture levels for AI agents.
Jul 28
3
Trace LLM workflows at your app's semantic level, not at the OpenAI API boundary
The data architecture for provider-agnostic reproducibility and experiments with LLM agents and workflows
Jul 11
3
1
Personal agents
Motivation
Jun 17
2
1
Architecture theory and the hourglass model
Everyone is talking about AI agent architectures, frameworks, and protocols at the moment.
Jan 8
3
1
Differential knowledge interconnection
This post is a reply to Eugene Kirpichov's post on Linkedin. Eugene writes that contributing to general AI and information processing capabilities…
Oct 12, 2024
2
Table transfer protocols: improved Arrow Flight and alternative to Iceberg
This article is the ultimate one in the five-piece series:
Sep 7, 2024
2
See all
Engineering Ideas
Ethics, AI Safety, physics of intelligence and agency, organisation and community engineering, methodology.
Subscribe
Recommendations
View all 7
Asimov’s Addendum
Asimov’s Addendum
Musings on the Alignment Problem
Jan Leike
Meaning Alignment Institute
Joe Edelman
Mental Contractions
Pawel Pachniewski
Sparks in the Wind
François Chollet
Engineering Ideas
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
