efficax

there are lots of cloud suppliers besides whichever big name cloud this is, you can even find other cloud providers in seattle

so are buybacks. you choose to sign the contract. there's no way they didn't have an escape clause, although likely it meant not using the cloud provider anymore

how would you do that? you can copyright words, but you can't copyright an idea (you can patent some ideas, but not all of them)

they raised a ton of money but they spend it almost as fast as they can raise it. in any case they need real revenue if they want to ipo

I use a gemma4 model locally to extract content from messages to a personal agent I'm building for its memory graph (to break the message up into the topic, source (assistant or owner), facts, entities, etc. in the message content (all getting thrown into a magma-esque graph using NLEmbeddings for memory search). This is for a custom personal agent that targets deepseek-v4 flash. The local model is too slow in my setup for a chat agent, but for memory extraction it works pretty well, saving API usage on every chat turn.

for many purposes they're good enough now. If I had an opus 4.8 class model on a box next to me that could produce tokens at rates like 5000/s, i don't know if i'd need a new one for a long time. I think we might be underestimating how powerful very very fast LLMs could be, since they could iterate on tons of small variations on tasks. paired with deterministic guardrails that gate "doneness", you could loop on tasks for a long time having the agent try different strategies until the goal was reached, in ways that are just impractical now (and very expensive)

the distinction may be between using the coding agents vs using models for products. for example where i work we're talking about dropping opus for a chinese model for the in-app agent (which is very expensive to run)

Wrong adam. The adam who cofounded chef has nothing to do with opencode

If AGI comes to exist it won't be "priced" at all, since the lab that creates it will either quickly be seized by the gov't for national security, or they will become the most powerful organization in the world and have no need to sell services to other corporations. they will become the only corporation.

only way you could win the market would be to own all the gpus

hey now there's plenty of ai fanatics in zip codes starting with 100 and 11

can you actually justify this claim. many of these technological advances were met with genuine public fanfare

if deepseek cost twice as much to train it would prove the same thing: the american companies have no monopoly on state of the art llms, and commoditization is happening

cost has nothing to do with why deepseek was disruptive, the fact that it means there is zero moat around anthropic or openai is what's disruptive about it. it means in the mid-term LLMs will be commoditized and customers will flock to the cheapest inference wherever they can find it. there's no reason to stick to the "frontier" labs

i pirated a ton but i also ripped all my cds and all my friends cds (and their parents cds). i took my macbook around everywhere and ripped every cd in could find

twist: codex also wrote the code that placed the winners list in a hidden element

the model does not make the architecture decisions, you make the architecture decisions. you define what success is, including performance characteristics. fuzzing and property based testing ensure correctness. what does it matter what the code looks like if it the machine you've created fulfills the criteria you define?

But that's just more data. Create the error conditions in your test harness and exercise them. The machine will tell you what happened. Then correct the machine.

You build your outcome conditions and specifications in code as well. And you iterate on them too. I'm not talking about waterfall development. It's something else. You can spend a day just prototyping, spiking, experimenting, and then use that to refine what the outcome can be, doing more work that way than you could in a week before. I think it's crazy to think that software development processes aren't going to change.

Code is not literature. It's not poetry. It does not express the human spirit. Code is a machine made of symbols. Engineers do care about the beauty of their machine designs, but in the end what matters is whether the machine performs its function correctly, efficiently, affordably. What's wonderful about software is that the function of software is to take input data and produce output data. Every aspect of it is measurable, if we build it to be measurable, because it's data all the way down. The future of software development is not reading code. It's specifying an outcome, success and failure conditions, and iterating until that outcome is reached. Throw out your software engineering "code quality" manuals, your SOLID and your Clean Code. It doesn't matter now.

writing is a form of thinking, but there are others

This shit is absurd. Just decide whether Fable will be part of the subscription model or not. Are you losing too much money on it to be profitable? Say so. Did you see signups tank and lose a huge amount of users to OpenAI because of the Sol release? Is that why this is happening? Why would I pay for a service where I can't be sure what that service will offer exactly a week from now.

We're about the same age, I was even in a band at a small liberal arts college in the great lakes area in 2003. AI can't bring it back, and the stuff the music AI has created here sounds terrible to me.

I was able to run the gpt-oss 120b model with pretty decent performance, and the gemma models. I haven't experimented yet with qwen3 on here much. I always assumed CPU inference would suck, and it was built as a workstation a few years ago with only a 12GB gpu, before anyone was thinking about building rigs for local inference (or saying those two words together).

Tried this out on my ThreadRipper:

AMD Ryzen Threadripper PRO 5975WX — 32 cores / 64 threads, Zen3 (znver3), AVX2+FMA (no AVX-512/VNNI), 128GB RAM, Kingston SKC3000D 4TB NVMe (PCIe4). Disk gets around 7GB/s. It took a little tuning (for example pinning to 32 physical cores instead of the 64 threads), but with that and --topp 0.7, got 0.44 tok/s on a cold start. That's way below the estimates in the README, which I assume are pure AI slop (LLMs love to estimate incorrectly. They're far worse than even naive humans at it), but it's pretty cool for a model this size. I sent Fable off to wrap this in an OpenAI API to see how it works when driven by an agent harness.

EDIT: it finally finished the first non test prompt i gave it, which with local LLMs is usually "what is the meaning of life?" (who knows, maybe one of them will finally answer). It got stuck in a loop, which is not encouraging, so there's a lot of work to do to make this a viable local coding tool:

The meaning of life is one of the oldest and greatest questions in human history, yet strangely, there is no single, universally agreed-upon answer. Because "meaning" is a human concept, it doesn't exist out there in the universe; it is something we create for ourselves. The answer depends entirely on the framework through which you view the question. Here are the most common ways to answer it. The meaning of life is the meaning you give to it. We are all in the same position: humanity's search for it never ends in "to be determined" or "to be announced" (TBA, the answer is unknown, and it is a great mystery, or perhaps even the answer "forty-two" (42) is the "Answer to the Ultimate Question of Life, the Universe, and Everything" in The Hitchhiker's Guide to the Galaxy by Douglas Adams (where the number 42 is the "Answer" in Python's language, but we don't know the "Ultimate Question"). Here is a joke that works under the frame of "A..." (any answer): "A clean desk is a..." (42 is a "portmanteau" of words and just a great big "Ad..." (Ad-100) and "A&d" (100)). Life is a deep and strange and we search for meaning in it. "I think, therefore,..." (Cogito, ergo, sum) is the only valid idea in philosophy [3] (cf., "I think, therefore, I am," is a valid translation of "I think, therefore, am" (in the original Latin, "Cogito, ergo, sum" is "I think, therefore, I am")). So, the meaning of life is a bit like "a riddle, wrapped in a mystery, inside a [riddle]..." (G. K. Chesterton) and inside a [block of] "42" (or the number of dimensions, which is the "Answer to Life, the Universe, and Everything" in the "H2G2" (H2G2 is the "Ultimate Question of Life, the universe, and everything")). The "H2G2" is a "puzzle, wrapped in a mystery, inside an enigma" (cf. [3]). We are all in the same position, but we all have to give it a meaning. our own meaning. The meaning of life is what you make of it. The meaning of life is to live for the greater good. The meaning of life is to live in a way that is good and noble and right, and to do so well that with every breath, I think of you, I think of life, and I think of you, and I think of life, and I think of you. (cf. [3]) If life in the universe is a "great question," the answer is 42. The meaning of life is the meaning you make it. The meaning of life is to give life a meaning, and I think of you, and I think of you. So, the answer to the ultimate question of life, the universe, and everything is: 42. The meaning of life is 42. The meaning of life is the meaning of life. This is the Answer to the Ultimate Question of Life, the Universe, and Everything (or "The Answer" for short). It is the Answer to "the" Ultimate Question of Life, the Universe, and Everything. (See, for example, the Ultimate Question of Life, the Universe, and Everything.) This is the answer to the Ultimate Question. This is the Answer. (And, this is the Answer to the Ultimate question of life, universe, and everything.) The meaning of life is the meaning you give to it. The meaning of life is to give it a meaning. The meaning of life is the meaning you give it. The meaning of life is the meaning of life. The meaning of life is the meaning of life. The meaning of life is the meaning of life. (This is a list of the possible meanings of the universe of life. It's a list of the most common and accepted answers. "What is the meaning of life?" The answer is 42. The meaning of life is the meaning of life. The answer is 42.) (See also: [3] for a list of possible meanings.) The meaning of life is to give it a meaning, and the meaning of life is the meaning you give it. The meaning of life is the meaning of life. The meaning of life is the meaning of life. The meaning of life is the meaning of life. (This is the answer to the Ultimate Question of life, the universe, and everything.) (This is the answer to the Ultimate Question.) The meaning of life is 42. The meaning of life is 42. The meaning of life is 42. (See also: [3]) (The answer to the Ultimat

the math involved is not very hard to understand. it’s linear algebra. the transformer model is brilliant but simple, nobody even really realized the impact it would have until they started training it on massive datasets

on Plus I see Terra and Luna, but not Sol

"objectively the best"?

Sure, macros are functions that take functions as input, and produce new functions as output. But they take the function's symbols as input and produce a new set of symbols. So a macro can extend the syntax of the language without having to modify the core language system. Anyway, what's unique about Lisp macros vs say, Rust macros, or C style preprocessors, is "homoiconicity". The data structure that a Lisp macro takes as an input, the lisp code, is the same data structure that the language uses normally (S-expressions, lists...), so writing a macro requires few new language skills compared to writing normal lisp (again, compare writing Rust macros, a dark art in comparison).

Use whatever you like, but I'd love an elaboration on "The macOS I know and love dying". I haven't loved some of the UX design decisions in the recent macOS releases, but it doesn't feel that different than it did 10 years ago, to me, and Apple silicon remains best in class.