https://hachyderm.io/@mitchellh/116580433508108130

Comments URL: https://news.ycombinator.com/item?id=48153379

Points: 1206

# Comments: 561

It is true that they were not transparent about the base model that they used until the model slug was discovered by a Twitter user via the API.

[1]: https://arxiv.org/abs/2603.24477 [2]: https://cursor.com/blog/real-time-rl-for-composer

We must be living in completely different worlds. Claude and other agents have completely upended work for me and every single other software engineer I know.

> The death I am describing has been going on for most of my life. The incident I am going to write about now took place last week, and it may even be halfway satisfyingly resolved within a day.

> I am not saying this incident “caused” any sort of republican death, nor am I saying it “ushered in a new era.” If this event contributed anything, it simply made the ongoing death more obvious and less deniable for me personally. I consider the events of the last week a kind of death rattle of the old republic, the outward expression of a body that has thrown in the towel.

Why do you think he is not bothered at all, when they publish post after post in their newsroom about the economic effects of AI?

The best-of-N feature is a bit like rolling N dice instead of one. But it can be quite useful if you use different models with different strengths and weaknesses (e.g. Claude/GPT-5/Gemini), rather than assigning all to N instances of Claude, for example. I like to use this feature in ask mode when diving into a codebase, to get an explanation a few different ways.

Comments URL: https://news.ycombinator.com/item?id=47021878

Points: 7

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=46741923

Points: 90

# Comments: 27

The limiting factors are typically: 1. Often there are latency/throughput requirements for model serving which become challenging to fulfill at a certain context length. 2. The model has to be _trained_ to use the desired context length, and training becomes prohibitively expensive at larger contexts.

(2) is even a big enough problem that some popular open source models that claim to support large context lengths in fact are trained on smaller ones and use "context length extension" hacks like YaRN to trick the model into working on longer contexts at inference time.

What's interesting is that the MGPU team has achieved SOTA Blackwell GEMM performance before Triton (which IIUC is trying to bring up Gluon to reach the same level). All the big players are coming up with their own block-based low-level-ish DSLs for CUDA: OpenAI, NVIDIA, and now Google.

Some more info in this issue: https://github.com/triton-lang/triton/issues/7392