Viewing profile — bjornsing

The concept is called static analysis.

Will Anthropic/OpenAI really hire anyone who can fine-tune an LLM?

I ran a small ISP around the same time that used this behavioral pattern to bring down the customer acquisition cost to near zero. Essentially we sold ADSL connections with Wi-Fi a…

To some extent I think that’s just human nature, or even animal nature. The optimal explore / exploit tradeoff changes as we age. When we’re children it’s beneficial to explore. As…

Yeah that’s sort of how I understand the OP too: The CPU will execute speculatively on the assumption that the next element in the linked list is consecutive in memory, so it doesn…

Yes. But I don’t think the OP is suggesting this as an alternative to using an array. As I read / skimmed it the linked list is just a simplified example. You can use this trick in…

But that works on a different level, right? At least as I understand it data speculation is about prefetching from memory into cache. This trick is about using the branch predictor…

Yeah I think this is a general principle. Just look at the quality of US presidents over time, or generations of top physicists. I guess it’s just a numbers game: the number of gen…

Yeah the whole methodology depends on forgetting about state and treating it as a long-running program. If you need to look at the state then you connect a debugger, etc.

Sure. But that’s just compression, right? I guess you could argue that some information is stored outside the genome, in the structure of proteins etc. But the counter argument is …

Swedish banks (even the Riksbank linked above) regularly refuse to turn cash into digital money unless you can ”prove” where you got it from. It’s not sufficient to say (with immen…

You’d have to explain where that innate knowledge is stored though. The entire human genome is less than a GB if I remember correctly. Some of that being allocated to ”priors” for …

The challenges around idempotency remain to some extent, yes. But you have that problem even in non-workflow code, so the usual patterns will just work with no extra mental effort …

Sure you get more control with explicit state management. But it’s also more work, and more difficult work. You can do a lot of writes to NVMe for one developer salary.

"Exactly-Once Event Processing" is possible if (all!) the processing results go into a transactional database along with the stream position marker in a single transaction. That’s …

> Yes, in any durability framework there's still the possibility that a process crashes mid-step, in which case you have no choice but to restart the step. Golem [1] is an interest…

But couldn’t an LLM search for documents in that enterprise knowledge base just like humans do, using the same kind of queries and the same underlying search infrastructure?

Exactly.

I doubt it was due to network effects. I’m probably one of those top quartile potential H1-B holders that never applied. My main reason for not applying is that the random nature o…

I guess it needs to get across the blood-brain barrier. But that shouldn’t take 10+ hours of surgery, I don’t think.

But it doesn’t take 10+ hours to surgically get a virus across the blood-brain barrier, right?

Why does it have to be delivered through brain surgery?

I’d say an LLM is a form of Markov chain, where the state is defined to consist of the entire context window, and each state transition adds one token to that context window.

> So for data centers, training is just as important as inference. Sure, and I’m not saying buying Nvidia is a bad bet. It’s the most flexible and mature hardware out there, and th…

> CUDA has been a huge moat The CUDA moat is extremely exaggerated for deep learning, especially for inference. It’s simply not hard to do matrix multiplication and a few activatio…