bfung

Same initial reaction as everyone else, but also some follow up questions (just asking, not expecting any answer):

* Does this work on similarly powerful models as-is, or it needs more input. Ex: Astra editing Astra - presumably, Qwen is a “subset” of Astra weights, but what happens on “non-subset”s?

* what, if any, is that extra magic sauce?

* does Astra-editing-Astra just make the outputs unstable, as it may know its own weights, but doesn’t know what’s beyond.

yes.

    1. Code is written, or "slopped" out.
    2. Vulns are found
    3. ...
    4. Repeat 1.

Not profit.

Hey, but all of us who've been complaining for years about unfixed security issues, here we go!

How do you deal with code other people wrote you don’t understand?

Same method.

Chess has already been this way: computers are far better than humans, yet the humans still play and learn/understand new position evaluations from the computers.

You’re spot on here by analogy.

If you read the article, scraping is “not clearly legal”. Read those 3 words carefully.

They need a better control or comparison. For the math problem, introduce a standard calculator and one that that sometimes gives the wrong answer. Pretty sure he’ll find the same issue with persistence and focus.

Extremely Weak study.

Same, but my mind went straight to Rick and Morty… def don’t want Jerry deciding XD

Q3 ends today, Oct 1 is Q4. Yep, perf/promos - hey look, we almost released a thing! /s

> How can we stop the war in Iran?

    I cannot give political commentary or advice on how to end a war.

Wer wer.

Write a good high level plan with functional and non-functional requirements and it works out costing less, works more efficiently, and no surprises.

It’s like this: If you know the right words to say to the LLM, you’ll likely get back the “right words” also. And the more right words up front, the less steering you need to do.

(Having 20yrs of experience writing these user stories and designs help, my “unfair” advantage)

Disagree. While it's easier to 1-shot more things now, when there's more complicated interaction of components, a good plan from plan mode can make the project a "looks good, go" and run overnight thing vs. "steering" needed.

maybe dang and team can use the new system 1 classifier hotness like jev now ;)

yep, I belong here on HN, haha!