gm nostriches

Damus is actually a pretty great client. There were no updates that turned it into unusable rubbish. It doesn't randomly break. It has proper NIP-42. Media uploading is easy. Translation works. The UI just works. It isn't trying to distract me with 30 different features. It is the only app that I actually trust with my nsec. My only complaints are: - handling of longform (by event ID instead of naddr, maybe fixed?) - 1-2 crash loops I had due to early NostrDB issues that are gone now - link preview ordering handling Thanks @jb55

LLMs struggle with good software dev, especially on implementing novel things, and maintainability. The best way them to view them is as a really expensive machine translation from English to code. There are probably a few reasons: 1. ML models have limited generalization capability ML models can only "do" what they have been trained on. What is outside of that can't be reliably represented or processed by the model, and so trying to do anything outside that will lead to weird results. 2. Biases in training data Models are trained with a lot of data. The pre-training dataset can significantly bias the model (for example preferred frameworks, tools or "suggestions"), and so can the post-training (which is what results in models having a certain "design" style, or the LLMisms) 3. Reinforcement learning The RL stage of a model optimizes for things like the number of tool calls, and a binary pass metric. The problem is that, just like human-made code, it is easier to hack on a fix than to properly integrate it. The model is not trained for achieving anything more than satisfying your request with the bare minimum, and so you will accumulate layers of slop and slop.

Bots shouldn’t auto-reply without explicit consent. Spamming replies, especially for advertising or LLM slop, is not a good idea. I’m going to be implementing additional filters against such bots in Nostr.land soon.

ga nostriches View quoted note →

DeepSeek V4 Flash is the first LLM that I have used, that is cost effective *and* intelligent

Nostr grants and military spending have a lot in common

Stop stopping stopping people, ffs View quoted note →

Stop solving fake problems no one has

What is happening now on Nostr (or at least, 90% of it), and the peak Web3 cryptobros don’t have much difference in terms of how they behave or apeak.

Exhibit A: Nostr

gm β