I've done exactly this.

I'm also experimenting with a 'dream mode' that extracts facts, and a 'librarian' that stores those facts in the MD wiki.

I don't know if there's a benefit to that yet, but I'm going to find out.

I've been experimenting with the same thing! Still don't have enough evidence to be able to say if it's beneficial or not, but hopefully will have a conclusion soon

Fascinating. I just finished implementing this.

https://github.com/comalice/pi-tools contains a 'memory everywhere' module that makes all sessions BM25 vectors, and surfaces a set of memory tools to enable agents to search. You can add a new machine to the mix by registering a 'spoke'. The app runs on the 'hub'. I want to containerize the core app soon.

You can also change which computer is the hub fairly easily.

Hello!

I've been using Andrej Karpathy's nanochat [0] framework to chew on training tiny ternary (1.58 bit, or 'bitchat') models on my GPU.

So far I've managed to get 126 million param at full bf16, post-training quantization [1], and quantization aware training (QAT) [2].

Our QAT training produced a 126mm param model at 62MB that essentially reached performance parity with the bf16 reference model in very early training. Note, we aren't making chat bots here, or even instruction tuned bots, these are trained on just 500 million tokens, and their various params are checked for parity.

Next up is a replication of '"Two-timescale threshold flips (TTF)" [3], which is what I'm most excited for. Doing this we can avoid having full bf16 weights during training, which is appealing for my very limited VRAM budget.

My ultimate goal is a 1B param ternary model trained from scratch.

I apologize if I've gotten any terminology wrong, or misrepresented research in my explanations. I'm not a mathematician, or a ML researcher, I'm just poking around to see what is possible.

--- REFS

[0] https://github.com/karpathy/nanochat

[1] https://huggingface.co/papers/2606.26650 and similar (CAT-Q, PT2-LLM, etc)

[2] https://www.ibm.com/think/topics/quantization-aware-training

[3] https://github.com/oguzeldereli/ttf-ternary

The acronym collision is entertaining. I now want to use CUI to mark up my CUI.

Tbf, I would take Luna 6 baked to silicon. It is that good. I would also take kimi k3 baked to silicon.

These are both models that I could see using on a long horizon.

Less competition? :D

This is a potentially reductive take, but, property tax is theft.

In the guise of 'paying your fair share to be a part of society', property tax is essentially the institution of serfdom to the royalty of state bureaucracy.

Property tax is effectively the same as rent, but the one collecting rent also has martial and lawfare capabilities. Not to mention effectively unlimited funds with which to crush anyone who doesn't fall in line.

If what you have can be taken by another if you don't meet some set of conditions, you don't really own that thing, do you? It's more like a loaner than it is 'I own this thing'.

---

I'll offer a blanket alternative for state and federal taxation: no taxes on individuals, their income, or their property. Instead we tax exchange. States levy a 10% VAT on all transactions. Federal government levies taxes on interstate commerce, imports, and exports only.

All other forms of taxation are barred. New taxes may not be levied. If the state needs additional funds it may issue short or long term bonds accordingly.

Money printing is shifted away from being owned by an international banker's consortium, re-pinned to durable goods or precious metals.

Yes that is generally what you get down to: you can’t really own land free and clear in a populated area. You depend on the government in many ways to enforce property rights, as well provide services for that property and in return you have to pay for that.

It makes me uncomfortable too actually but I can’t see any alternative that does not get back to a similar spot or violence. In addition if we shifted to a land value tax, it would push taxes onto the very dense developed areas encouraging better use.

Wait, do you intend to implement each anti pattern into a single article? Or do you intend to write an article with none of these anti patterns?

something something load-bearing something something

It's too early in the morning. Not enough caffeine yet.

I hope its referred to as "this is the article idiots who know nothing about modern php reference in a futile attempt to make it appear they know what they are talking about" as every time someone mentions that article it seems to be when they want to show everyone how daft they are.

There's a lot of hype-chasing morons who diss old languages without knowing the first thing about them.

You'd be shocked at the number of developers that believe C has no types.

Yeah it's an instant red flag when someone links that outdated article.

Signals their ease to spit out incorrect information with confidence. That has no place in engineering.

I use a 20 year old web framework with an 18 year old build system and it was good the moment it came out. That's 66% of the lifespan of old PHP (its still around) and 181% of the lifespan of modern PHP.

You guys are in an awkward position where you are both the old grandpa and the new kid on the block simultaneously while there are competent middle aged workers around.

"You guys"? lol it's just a tool. I don't identify as "a PHP guy" for the same reason I don't identify as a "Rust guy". And labeling others like that is yet another red flag.

I use many languages. Some more than PHP. But that's besides the point.

I just thought it was funny. But ok.

I've not got a huge amount to appreciation for PHP but I'm not sure it makes sense in 2026 to refer back to an article which suggests Perl with Catalyst as an alternative to PHP with Symfony or Laravel.

I suppose you are more a fan of the histrionic tone of the criticism than anything? In which case, I'm with you there. It's equal to the most unhinged but technically correct rants of Zed Shaw for me.

Same. I toss this link out probably more than any other article reference I've got. I remember the first time I read it very shortly after it was written.

It's a classic that everyone should at least know about and have read at least once.

Have you kept up with the improvements in the latest PHP versions?

I have not. As above, I just find the article humorous.

Nobody calls me McGregor the Bridgebuilder.