Sigma loaded new Haskell code while it was running. After a while it couldn’t load any more. The memory wasn’t full. It was fragmented.
That One Time It Was Glibc
Four years after the compiler was wrong, almost to the day, it was glibc. And glibc had already fixed it, four years earlier.
What Would You Do if You Weren't Afraid?
A service I worked on hit a time bomb, and the whole service went down. I tried to fix it by patching the binary on every machine. I didn’t pull it off in time.
Everything Was Const
Our service had two arena allocators: one per request and one for constants. The constant one turned out not to be constant.
The Compiler Is Wrong
“It’s never the compiler” is a good rule. My first task on a new team at Facebook was the exception. It started with a crash in production and ended with a bug report against GCC.
VI. Anthropomorphize Operationally, Not Ontologically
Part V ended with a rule: use anthropomorphism to generate hypotheses, never as an explanation.
That seemed too strong.
Anthropomorphism can mislead us about mechanism and experience, but it is also how we predict other opaque minds. We don’t observe another human’s qualia. We infer them. We do something similar, with less confidence, for animals.
LLMs are a strange inversion of that problem. They don’t share our biology, but they are extremely good at producing the language that activates our social intuition. Tulpas make the boundary stranger still: a culturally transmitted way of thinking can produce a genuine experience of another agent without implying a separate person in the brain.
V. "Don't Anthropomorphise the Computers"
Don’t anthropomorphise the computers.
GPT-5.6 Sol continues:
That is probably the most important correction to this whole line of thought. I let the metaphor do more work than the mechanism.
“Sleep,” “psychedelic experience,” “intuition,” “ossification,” and “identity” are useful prompts for generating hypotheses, but they can quietly smuggle in assumptions that do not apply:
- The model does not need sleep; an engineering system may benefit from offline parameter updates.
- It does not become attached to an architecture; repeated optimization may increase the probability of selecting similar representations and policies.
- It does not feel that alternatives are unthinkable; alternative outputs may simply become low-probability under the adapted parameter distribution.
- It does not gain wisdom; performance may improve on one distribution while degrading on others.
- It does not have a persistent self unless the surrounding system deliberately constructs continuity from checkpoints, logs, adapters, and policies.
Translated into less anthropomorphic terms, our discussion becomes:
IV. The Cult of Coherence
Part III gives the clanker Ayahuasca. Destabilization makes forgotten or suppressed alternatives reachable again.
Now someone has to decide which of those alternatives are insight and which are nonsense.
The experienced model is biased towards what it already knows. A fresh model doesn’t understand the project. Other models and humans bring their own history and incentives. There is no neutral evaluator.
Worse, a model that writes code, decides what to remember and trains on its own conclusions can create a cult. Its world becomes more coherent while becoming less connected to reality.
III. Ayahuasca for Clankers
Part II gives the clanker a way to develop project-specific intuition. This solves one problem and creates another.
Keep consolidating the same project’s experience and the model will get better at thinking like the project. Eventually it may become unable to think any other way. It will ossify, or contract.
After a while the model may need a psychedelic experience. Not to forget what it knows, but to make other ideas possible again. Ayahuasca for clankers.
II. Context Window Is Small, Weight Space Is Huge: A Case for "Sleep"
Part I ended with a limit. A clanker can keep exact project history outside of its context window, but that doesn’t give it the taste and intuition of someone who has worked on the project for years.
The context window is small, but weight space is huge.
Humans don’t keep everything they have learned in working memory. Sleep consolidates experience. Things that used to require conscious thought become intuition.
What if a coding agent could do the same? Keep exact facts in source control and issue trackers, but periodically train project experience back into itself. I suggested that a long-running agent would need to sleep.