#Development #Guides
Context engineering · Bringing engineering discipline to prompts https://ilo.im/165cxw
_____
#Programming #Mindsets #AI #AiAgents #ContextEngineering #Prompting #SystemDesign #WebDev #Frontend #Backend
#Development #Guides
Context engineering · Bringing engineering discipline to prompts https://ilo.im/165cxw
_____
#Programming #Mindsets #AI #AiAgents #ContextEngineering #Prompting #SystemDesign #WebDev #Frontend #Backend
No one signed the denial. No one made the decision. But the harm arrived anyway.
New short film: The Disappearance of Accountability
Companion post: The Bureaucratic Abyss
Kafka foresaw the system. We built it.
Watch + read: https://redefine.pt/2025/07/10/the-bureaucratic-abyss/
https://youtu.be/M754BTKTjXM
Permaculture: Social & Legal Design
Designing systems where care, cooperation, and justice grow as naturally as the forests.
Drawn from Bill Mollison’s "Permaculture: A Designer’s Manual"
https://jpst.it/4r3NJ
Part1: #dailyreport #agents #agent #agentsystems #multiagent
#llms #systemdesign #softwaredesign #softwarearchitect
#systems #multiagents
Topic: Building Agent Systems and Model Context Protocol (MCP).
I see that designing AI systems is like normal software
development. We define business needs, boundaries, and
resources, but we think in an agent-oriented paradigm,
which is much more highly abstracted. For example, we
can define a party of agents with roles and rules,
adjusting only part of it at every task. We may choose
the level of abstraction to define a life form with its
goal, replication, ethics, and "self" conscious, or a
bunch of bacteria that just react to the
environment.
The question is how bacteria should learn
and adapt, and not to ask bacteria to think about
"Organizations which design systems (in the broad sense used here) are constrained to produce designs which are copies of the communication structures of these organizations."
— Melvin E. Conway, 1967, in How Do Committees Invent?
"Un système complexe qui fonctionne est toujours issu d'un système simple qui fonctionnait.
"Un système complexe conçu à partir de zéro ne fonctionne jamais et ne peut pas être modifié pour le faire fonctionner.
"Il faut repartir d'un système simple qui fonctionne."
John Gall, 1975
"A complex system that works is invariably found to have evolved from a simple system that worked.
"A complex system designed from scratch never works and cannot be patched up to make it work.
"You have to start over with a working, simple system."
—John Gall, 1975
cited and explained by @baldur there: https://www.baldurbjarnason.com/courses/yellow/
A reflective take on how modern systems—from social media to certifications—reward surface-level wins over deep effort. This post explores how we’ve learned to game metrics, optimize for the minimum, and lose sight of meaning in the process. It asks: what happens when the game replaces the goal?
Hearing from an old colleague that your system design scaled and survived for many years is a really nice confirmation.
In this case it was my first multi-process, distributed project based on what I learned from #OpenBSD daemon design and reading #UNIX Network Programming by Stevens, using #SQLite, sockets, select, fork/exec, dropping privileges, passing jobs to distributed workers, and even running on different platforms. Simple, effective, and pretty scalable.
#SystemDesign #ThrowbackThursday
I’m starting to think that anyone who designs or builds systems that handle data should do a basic bookkeeping course that covers how double entry works.
The accountants managed to work out for us since the 13th Century that if you move money from A to B, both A and B need an audit entry describing the movement each way. Write only - nothing is removed. Yet I don’t see an equivalent teaching in the various system design books, despite this concept being fundamental to any system that needs (financial and non-financial) auditing capabilities.
Ok, my turn to write an #introduction full of as many hashtags as I can think of.
I am in #infosec for as long as I can remember. My main interests in the subject are #networksecurity, #websecurity, #codereview, and secure #systemdesign. Unfortunately for you (and probably for me too, I don't know at this point) I also have a Ph.D. and I am a huge fan of "The Logic of Scientific Discovery" by Karl Popper.
I also like #movies, I watch a lot of them and I make way too many references, like the one below.
While waiting for my letter from #Hogwarts, I practice my dark arts with #computerscience the only other thing close to magical spells that I know how to cast.