Jhet Chan

a tale of illusion. in physics, mathematics, and cognitive science, we don't usually call it an illusion, we call it an abstraction, an effective theory, or a representation. because the cost of total truth is infinite. to model trajectory of a thrown baseball "perfectly", we'd need to simulate every particle and their quantum interactions. there is not enough computing power in the universe to do that. so we use the 'illusion' of classical mechanics pretending the baseball is a single object with a center of mass to give us clean trajectory. neural systems do the same. reality is a continuous, high-dimensional chaotic mess. so the system compresses it onto a low-dimensional manifold and forces stable representation. even computers, rely on illusion with perfect 1s and 0s with noisy continuous voltages underneath without these collapses there would be No categories No logic No beauty just an infinite stream of white noise. a bad illusion is one that fails to predict reality. a good illusion is not truth but a structure that preserves what matters any system that acts must hallucinate a simpler world and then live inside it. it is the only way an observer can zoom out far enough to actually interact with the universe without being paralyzed by its infinite complexity.

instead of … “Is what we are seeing the reality? ” try the alternative: “what invariants of the world survive this projection pipeline? ”

Don’t try to learn the whole terrain. Learn how to move safely on the parts you’ve seen and recognize when you’re at somewhere new.

take one weird thing and make it undeniable.

it's either stabilises into something real or it doesn't it's either anchors to a reality where something observable, testable, repeatable, and holds when pressure is applied… Or it's vapor. No poetic license. No "it depends on perspective" No "my truth vs your truth" if the claim, model, belief, or system cannot be stress-tested against what actually exists (independent of wishes, narratives, or social consensus), then it fails the test. it doesn't stabilize anything real then it's merely a decorative noise that collapses under its own weight the moment reality pushes back. not everything has to survive the test. but it has to survive where it matters

we thought we were pursuing something but in parallel, in the process, we were being shaped into someone who optimizes that system

progress is mostly about eliminating illusions

if failure is specific rather than random, then it means the failure has a structure. And structure is exploitable.

some truths can't be reached from where we currently stand, no matter how valid they are. The path has to exist, not just the destination.

2 dispatch bugs found by dogfooding exoprotocol on a real project: - priority was inverted (5 dispatched before 1) - epics got dispatched as work items the agent figured it out by reading its own reasoning trace. fixed in v0.1.27. pypi.org/project/exopro…

agentic coding has made code generation trivial. the catch: if a requirement can't produce executable proof, then it's a liability, a slop ideally: spec → .md rules → agent codes → test → ci gates misaligned code = build fails. here's a take to turn spec into infra, not to slow things down but to keep things aligned. exoprotocol.ai/blog/spec-to-g…

exoprotocol update: Agent Handoff: session-handoff atomically transfers work between agents. Agent A finishes, writes a handoff record with summary + next steps, releases the lock. Agent B starts and gets the full context injected into its bootstrap. One-shot, no stale context. CI Auto-Fix: exo ci-fix --apply --push fetches failed GitHub Actions logs, parses ruff/pytest/compile errors, auto-fixes, pushes. One command to close the feedback loop. SDK Hooks: ExoRunHooks wraps governed sessions around OpenAI Agents SDK runs. Claude Code hooks auto-start/finish on lifecycle events. but of course, you don't run these commands anymore, your AI agents do. just ask your agent to start using exoprotocol.dev 🤖

tldr;

multiple AI agents vibe-code on the same repo (or across multiple repos) = high entropy. 🤖🦀🤖🦀 things break silently... scope collisions, forgotten context, semantic drift and ungoverned commits... built exoprotocol to fix this. it's a governance kernel that gives each agent session a ticket, a scope fence, and a paper trail without leaving git. think OS but for AI coding agents pip install exoprotocol exoprotocol.dev 🤓 check it out