Recent submissions

Comment · 12 days ago
Like the example they used in the blog is terrible. Weekdays wouldn't need any symbols. A cogwheel for settings is a great example.
Comment · 27 days ago
For me the page just reloads no matter where I click.
Comment · 1 month ago
I think most of the comments are talking about the some "virus" but the actual valuable part of the paper is about making choices when interacting with LLMs in such a way that abilities are reversable. That you are still able to do those things without LLMs. And that society and institutions help to preserve this ability by encouraging ways to do things with and without LLMs.
Comment · 2 months ago
Why not use Codex for that? What is the differnce between work and codex for a very specific task that involves terminals?
Comment · 2 months ago

                       agent memory
                             |
              +--------------+--------------+
              |                             |
       deductive state               episodic memory
              |                             |
       facts / rules / time          fuzzy context
       provenance                    semantic retrieval
       retractions                   source text

Well this turns out, just like human memory functions. (Semantic vs episodic memory)
Comment · 2 months ago
People are not talking enough how huge this is for robotics and IoT. Current robotics arhitectures are limited by tok/sec. How cares if its not a Fable model?

This move undercuts NVIDIA directly.

Comment · 2 months ago
Comment · 3 months ago
"The forces that destroyed SA were also what generated its 4×+ return"...yes, that is what levrage means? And it goes both ways.

The interesting part what this article states: SA was essentialy a thematic ETF without any hedging to buffer downside, and got margin called.

Comment · 3 months ago
Have $300k in disposible income?
Comment · 3 months ago
So I have to Shift + Alt + n, the search for the HN blog / article in the other tab? If you have a lot of tabs this isn't feasable.
Comment · 3 months ago
Wouldn't it make sense to have it an extension? Just spontainously (without reading any instructions) I don't understand how to use this or what Userscripts Tamper or Violentmonkey is.
Comment · 3 months ago
How about;

1. Make anti-distillation clauses illegal to strenghten western opensource eco-system.

2. Make cyber-defensive models widely available (can detect but won't operationalize vulnerabilities). Otherwise make Fable awailable for everyone. Keeping the cybersecurity in assymetry by withholding cabailities just causes more instability and increases the incentives for powerfull close sourced models. This is a loss for everyone.

Comment · 3 months ago
When a frontier makes a succesfull edit based on the plan that it made, it leaves an procedural trace in turn biases the NEXT model, low cost model, straight into procedural action. The cheaper model doesn't need to reread everything again because it has enough information from the frontier model to complete the task. A simple "plan" of what needs to be done does not carry this information.
Comment · 3 months ago
Yes this is correct. It essentially biases the cheaper model into procedural action grounded by the frontier model. To put it mode generally, it injects the cheap model context with more useful information, where it might not need to read all the files again.
Comment · 5 months ago
There is more to it than typing "llama serve".

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton