Viewing profile — RandomBK

Laziness and weak connections makes sense as differentiators. However I'm not sure Excel is such a great illustration in that case, as it's neither lazy nor weakly connected; at le…

One thing I've never fully grokked is how this differs from an observable pattern where one can publish new values to inputs, propagate that through the computation, and push newly…

I'm curious to hear what bottlenecks you encountered in the traditional path. Of all the compute and data shuffling involved in LLM inference, I would have thought shuffling the ra…

As someone who uses gradle largely out of inertia, I'm curious what you would pick as a better alternative.

I've found swearing at a model to be quite effective in getting it to rethink and correct its mistakes. This seems to apply across Codex, Claude, Qwen, and Gemma/Gemini. I don't kn…

> context with 2.1 bits of entropy per token Can you elaborate on this? I'm seen estimates of ~1.5bit per English letter , and tokens encode a lot more than that - sometimes full w…

VPS comes at the cost of potential for oversubscription - even from more reputable vendors. You never really know if you're actually getting what you're paying for.

One annoyance (I don't know if they've since fixed it) was that Docker Hub would count pulls that don't contain an update towards the rate limit. That ultimately prompted me to swi…

How well do we understand the tokenization for Claude? I'd posit that the exact human-representation of this markup is likely irrelevant if it's all being converted into a single t…

Code length will itself become a problem. The instruction cache is limited in size and often quite small. Bloating instruction counts with lots of duplicated code will eventually h…

Additionally, so long as we can be sure the human's output is not actively adversarial , we can xor it into the entropy pool. Entropy can only increase this way.

I'm reminded of a diagram from the pitch doc for the original Diablo [0] that made its rounds across the web recently. The dungeon/town split was particularly sharp back then, but …

Good catch; it was somewhat ambiguous in the report.

I see a lot of discussion in this thread stemming from some confusion+not reading the actual report[0]. Some key points: 1. The Camera+Card was encased in a separate enclosure made…

> Getting on the public suffix list is easier said than done [1]. Can you elaborate on this? I didn't see anything in either link that would indicate unreasonable challenges. The P…

Chatterbox TTS from ResembleAI ( https://github.com/resemble-ai/chatterbox ) is one of the most accessible and highest-quality Voice Cloning models available today. However, its im…

My 2c is that it is worthwhile to train on AI generated content that has obtained some level of human approval or interest, as a form of extended RLHF loop.

It reminds me of the early days of Typescript rollout, which similarly focused on a smooth on-boarding path for existing large projects. More restrictive requirements (ie `noImplic…

I saw an April Fools joke and decided to implement it. This is a rough port of llm.c into a kernel module. A lot of hacks were needed to make this happen, so a lot of performance w…

The way the question was framed, it was ambiguous whether "draw again" only applied to B, or whether A would draw again as well. I'm assuming the 'infinity' answer applies only to …

> IEEE754 is not great for pure maths, however, it is fine for real life. Partially. It can be fine for pretty much any real-life use case. But many naive implementations of formul…

The entire frontpage was just 468KB, 91KB compressed, and most of that was the search index. Very neat!

You mean $2/customer? That doesn't actually sound that bad, and is in line with many other marketing efforts.

Yup. I was referring to the 1.58B quant which seemed to be performing alright and would be the smallest real-DeepSeek model. That requires ~140GB, which is just barely doable on a …