Viewing profile — nostrebored

Professors have no reputation for writing good code. Academic code is fairly notorious for being under abstracted, hard to follow, messy, etc. If a passerby told me this story I’d …

why?

it sounds like a bad abstraction. ime llms are really bad at reasoning through efficiency and utilization problems. they fail at scheduling and bin-packing for the same reason. it'…

It was sarcasm. It's also not particularly insightful. "AI data centers" get immense scrutiny right now. Astoria has a similar generation capacity in a much denser (and human popul…

"Small" was a poor choice of words here, "low compute budget" is more what I'm getting at. In voice interactions, ttfat is actually relatively important. If you look at models with…

For customer support I don't think models have gotten better since gpt-4.1. The class of small models, with limited to no reasoning, that need to handle a complex issue with a touc…

but... why? you almost never want these tools in any given session, and creating any of them can be done simply with Claude. looking at the PRs, it seems like that is exactly what'…

we're always in uncharted territory. that's why most HN commenters think that this is hyperbole.

It’s in the weights. Context needs to be attended to to create a response, and the weights dictate what response is decoded. If you include retrieved context that has an American p…

it is pretty good at instruction following and has extremely fast decode.

qwen3.6 starts at 27B

Oh I agree with you, it's just that I don't think LLMs are either. If you think of LLM knowledge, especially in scientific/engineering fields, as a lossy representation of the dens…

Daily allergy tablets are associated with huge increases in early onset Alzheimer’s. Glad you found something that works, but might be good to get some of the allergen injections :…

I don’t understand the negative reactions. Medical care as it exists requires the doctor and patient to have their brains switched on. I’ve almost never had a problem where a docto…

Claude is the worst FM at image understanding. Prior to gpt-5.4 the only usable models were Gemini and Qwen.

But the binary classification models can be made ternary easily. RL on congruence plus penalty for misdiagnosis is easy to set up and gives great results. What I’ve seen be the tru…

I think that much of the visual gap is because what to attend to in images is less structured. Anecdotally small qwen finetunes (ie less than 10B) take task accuracy from sub 30% o…

He made it happen by continuously using doomsday marketing to pump up model capabilities. This is the comeuppance. There is a huge contingent of people who do not interact with AI …

Well if you can do this then you don't delegate execution path derivation to the agent. The benefit is a predictable coherent world state where you understand the impact of { curre…

The leakage problem is so pervasive. None of the frontier models seem to have any idea how to actually hold out rows. God help you if you decide to change the data mix. I was worki…

Building an ontology of how people think of and organize information, processes, and actions is not solved via markdown. It’s not well solved intra company much less inter. The sys…

I strongly prefer codex. Claude is annoying. Codex provides descriptions where I want them and more touchpoints to audit the quality of work. Claude code on experimental seems to n…

But how many plugins are people actually using? I can think of one MCP server I find valuable (context7) and one plugin that i've installed, but continuously think about uninstalli…

LLMs are obsessed with “gates”. Freezing the gates here is intuitive to me as this point — don’t let validation drift.

But why does your agent control doneness? It seems to me the most odd part to delegate. All LLMs are terrible at it. Most LLM tasks can be expressed as a DAG or DAG of DAGs. Why de…