graemefawcett

no profile record

Submissions

SyneState: Machine Synesthesia with Manifold-Constrained Hyper-Connections

2 pointsby graemefawcett6 เดือนที่ผ่านมา1 comments

DNS as a Filesystem: A Practical Study in Applied Category Theory

1 pointsby graemefawcett7 เดือนที่ผ่านมา3 comments

[untitled]

1 pointsby graemefawcett7 เดือนที่ผ่านมา0 comments

Abusing DNS TXT Records as a Planet‑Scale Key‑Value Store for Fun (and Geese)

graemefawcett.ca

1 pointsby graemefawcett7 เดือนที่ผ่านมา0 comments

Loss.md

1 pointsby graemefawcett8 เดือนที่ผ่านมา0 comments

I Built the Perfect Workflow and attracted some friends in the process

graemefawcett.ca

3 pointsby graemefawcett9 เดือนที่ผ่านมา1 comments

I built a translator for spatial thinking (because I can't interview in Python)

graemefawcett.ca

2 pointsby graemefawcett9 เดือนที่ผ่านมา1 comments

comments

2 เดือนที่ผ่านมาdiscuss

The other cases are the original request is still in flight or never occurred. The former case was explained by the prior comment, one request is processed, the other is returned by 409. The system cares little for which is which and neither should the caller. The latter case is handled by clients retrying until a request is received, at which point one of the other three states takes over.

Whether or not a prior request exists in the system in processed or unprocessed state should not matter in a properly implemented idempotent system, the whole point is that one and only one is processed, and all replicas indicate that they are such.

What you do inside of your boundary to implement that idempotent contract need not be part of the contract and the decision of what primitives to use (locking, content-based addressing etc) are mainly just a question of implementation constraints.

3 เดือนที่ผ่านมาdiscuss

Stateless router to router with lossy scratchpad is a step up, still not going to ask it to check my Lisp. That's what linters are for

3 เดือนที่ผ่านมาdiscuss

RAG is like when you want someone to know something they're not quite getting so you yell a bit louder. For a workflow that's mainly search based, it's useful to keep things grounded.

Less useful in other contexts, unless you move away from traditional chunked embeddings and into things like graphs where the relationships provide constraints as much as additional grounding

3 เดือนที่ผ่านมาdiscuss

It's not just an issue of tokenization, it's almost a category error. Lisp, accounting and the number of r's in strawberry are all operations that require state. Balancing ((your)((lisp)(parens))) requires a stack, count r's in strawberry requires a register, counting to 5 requires an accumulator to hold 4.

An LLM is a router and completely stateless aside from the context you feed into it. Attention is just routing the probability distribution of the next token, and I'm not sure that's going to accumulate much in a single pass.

4 เดือนที่ผ่านมาdiscuss

Exactly. They've implemented a VM inside a transformer, turned an O(1) memory access call into O(n), optimized it down to O(log n) and wrote a post about how smart they are.

It's a nice bit of engineering, if you don't subscribe to YAGNI. If you do, you must ask the obvious question of what capability this delivers that wasn't available before. The only answer I've got is that someone must have been a bit chilly and couldn't figure out the thermostat

4 เดือนที่ผ่านมาdiscuss

Basically just madlibs - the models generate intermediate tokens that help predict a better answer based on training (RLHF & otherwise). They tend to look like "reasoning" because those tokens correlated with accepted answers during training.

Extended thinking passes are just more of the same. The entire methodology exists merely to provide additional context for the autoregression process. There is no traditional computation occurring

4 เดือนที่ผ่านมาdiscuss

I believe that's I and the paper are both saying as well. The LLM is pure routing, the constraints currently are located elsewhere in the system. In this case, both the constraints and the motivation to perform the work are located in Knuth and his assistant.

Routing is important, it's why we keep building systems that do it faster and over more degrees of freedom. LLMs aren't intelligent on their own, but it's not because they don't have enough parameters

4 เดือนที่ผ่านมาdiscuss

This is exactly how problem solving works, regardless of the substrate of cognition.

Start with "all your questions contained in randomness" -> the unconstrained solution space.

The game is whether or not you can inject enough constraints to collapse the solution space to one that can be solved before your TTL expires. In software, that's generally handled by writing efficient algorithms. With LLMs, apparently the SOTA for this is just "more data centers, 6 months, keep pulling the handle until the right tokens fall out".

Intelligence is just knowing which constraints to apply and in what order such that the search space is effectively partitioned, same thing the "reasoning" traces do. Same thing thermostats, bacteria, sorting algorithms and rivers do, given enough timescale. You can do the same thing with effective prompting.

The LLM has no grounding, no experience and no context other than which is provided to it. You either need to build that or be that in order for the LLM to work effectively. Yes, the answers for all your questions are contained. No, it's not randomness. It's probability and that can be navigated if you know how

4 เดือนที่ผ่านมาdiscuss

Connecting them is easy, one is the math of the exchange and one of the state machine.

A better question might be why no one is paying more attention to Barandes at Harvard. He's been publishing the answer to that question for a while, if you stop trying to smuggle a Markovian embedding in a non-Markovian process you stop getting weird things like infinities at boundaries that can't be worked out from current position alone.

But you could just dump a prompt into an LLM and pull the handle a few dozen times and see what pops out too. Maybe whip up a Claw skill or two

Unconstrained solution space exploration is surely the way to solve the hard problems

Ask those Millenium Prize guys how well that's working out :)

Constraint engineering is all software development has ever been, or did we forget how entropy works? Someone should remind the folk chasing P=NP that the observer might need a pen to write down his answers, or are we smuggling more things for free that change the entire game? As soon as the locations of the witness cost, our poor little guy can't keep walking that hypercube forever. Can he?

Maybe 6 months and a few data centers will do it ;)

5 เดือนที่ผ่านมาdiscuss

[flagged]

6 เดือนที่ผ่านมาdiscuss

[dead]

6 เดือนที่ผ่านมาdiscuss

I think the biggest benefit is bandwidth more so than efficiency. This gives you multiple streams to mux which and a means to control their mixing.

The biggest innovation I think may have been accidental. The doubly stochastic matrix implements conservation on the signal stream.

Treating the signal like the information it is as we do in any other domain is crucial for maintaining its coherence. We don't allow a network router to generate more packets than it receives for the same reason.

6 เดือนที่ผ่านมาdiscuss

Are you aware that there are certain members of your very own species that are as intelligent as you or I, who lack those qualia.

Non standard cognitive architectures are already coherent. Even if they were, why do you think qualia cannot be replicated with a similar signal to semantic meaning? Are there additional dimensions that we can feel that we've never talked about or more importantly, written down?

6 เดือนที่ผ่านมาdiscuss

I took that idea just as far as I could and landed here

https://zenodo.org/records/18181233

It parses the AST out of it and then has a play

We're using it as an agentic control plane for a fortune 500s developer platform.

Keep going with yours, you'll find it

6 เดือนที่ผ่านมาdiscuss

We propose SyneState: a communication prosthetic built on DeepSeek's Manifold-Constrained Hyper-Connections (mHC) architecture. By parameterizing cross-channel mixing as a doubly-stochastic matrix constrained to the Birkhoff polytope, we can: (1) induce machine synesthesia—stable, tunable cross-modal binding between latent streams; (2) learn personalized binding matrices that approximate individual cognitive architectures; and (3) translate between compression levels—expanding high-compression encodings into explicit single-channel representations and vice versa.

  For mHC implementers, SyneState is a direct application of manifold-constrained mixing to cross-modal binding. For cognitive science and clinical researchers, it offers a candidate prosthetic for the double-empathy problem: bridging communication gaps not by "fixing" either party, but by learning the translation between different cognitive compression schemes.

  All required components—multi-stream residuals, Sinkhorn projection, multimodal attention heads—exist in production stacks today. This is integration work, not research.

7 เดือนที่ผ่านมาdiscuss

Besides, if everyone could paint the Sisten Chapel, then we'd have works equivalent to the Sistene Chapell everywhere.

Why is that a problem?

That to me sounds like the opposite of a problem.

Used effectively, these tools are elevators, enhancing the capabilities of everything they touch.

Telling them to paint you a picture results in the word you envision.

Painting a picture with them is how you see mine

7 เดือนที่ผ่านมาdiscuss

Is art then just the outcome? The artifact that was produced?

What's your criteria then for who is allowed to produce art? If allowing everyone to create it lessens its value such that it becomes worthless, there must be a cutoff.

If your goal is to ensure the continuity of human expression, limiting who is allowed to create art and narrowly defining art to great works kind of misses the point.

7 เดือนที่ผ่านมาdiscuss

I've been doing it for months, it's lovely

https://tech.lgbt/@graeme/115749759729642908

It's a stack based on finishing the job Jupyter started. Fences as functions, callable and composable.

Same shape as an MCP. No training required, just walk them through the patterns.

Literally, it's spatially organized. Turns out a woman named Mrs Curwen and I share some thoughts on pedagogy.

There does in fact exist a functor that maps 18th century piano instruction to context engineering. We play with it

7 เดือนที่ผ่านมาdiscuss

I had a sickie yesterday with nothing better to do than attempt to prove isomorphism across domains

Like drawing lines on a mids menu but for grown ups when the price is right isn't on

7 เดือนที่ผ่านมาdiscuss

Two systems are isomorphic when they admit the same morphisms—when the set of valid transformations applicable to one equals those applicable to the other.

If Hom(X, DNS) ≅ Hom(X, Filesystem) for all relevant X, then DNS ≅ Filesystem.

Wherein we prove it is