HackerTrans
TopNewTrendsCommentsPastAskShowJobs

cheevly

8 karmajoined 5 tahun yang lalu
Building a generative operating system: Seed OS

Submissions

[untitled]

1 points·by cheevly·8 bulan yang lalu·0 comments

comments

cheevly
·17 jam yang lalu·discuss
Maybe like… focus on the actual content instead of perceived writing patterns? Crazy I know.
cheevly
·8 hari yang lalu·discuss
The irony of this article is thick.
cheevly
·17 hari yang lalu·discuss
I'm pretty sure programmers weren't the ones writing the specs in the past...
cheevly
·17 hari yang lalu·discuss
Lacking willpower sounds biological to me... do you disagree??
cheevly
·bulan lalu·discuss
If yours cant, then I implore you to find better AI mediation tools.
cheevly
·bulan lalu·discuss
GPT literally generates perfect code for me in languages that do not exist anywhere in its training set, so I’m not sure how you’ve achieved this level of failure.
cheevly
·bulan lalu·discuss
Ever since the first Davinci model of GPT-3 ive literally been using LLMs daily. It was an indispensable tool for me from the very beginning and despite 10,000+ hours of usage and research, I still feel like ive barely cracked the surface of whats possible with current genai tech.
cheevly
·bulan lalu·discuss
When I use AI to produce a work, it’s human-made, just the same as when I use a computer to synthesize digital works using human-developed automation tools like word processors. All built on top of operating systems that manipulate bytes of all natural human-made data.
cheevly
·bulan lalu·discuss
This is a great answer.
cheevly
·bulan lalu·discuss
[flagged]
cheevly
·bulan lalu·discuss
Yeaahh, that you assert that makes your point says a lot.
cheevly
·bulan lalu·discuss
[flagged]
cheevly
·bulan lalu·discuss
I think the prevailing answer is lack of evidence, with things like suffering / death and stuff as a close second.
cheevly
·2 bulan yang lalu·discuss
Imagine classifying Apple as AI experts. You are lost my dude.
cheevly
·2 bulan yang lalu·discuss
It really sounds like you’re doing it wrong (using multi-agent patterns of yesteryear).

The proper way is to use multiple agents for work involving very large context, and splitting the context amongst them. It effectively enables encapsulation and separation of concerns, which yields much clearer benefits when working at scale.
cheevly
·2 bulan yang lalu·discuss
Agents are perfectly capable of learning. Why would the model need to learn? The harness and tooling are all that matter.
cheevly
·2 bulan yang lalu·discuss
This is my experience. Though ice been writing LLM harnesses, agents, tooling, etc for 5 years now and believe it requires several hundred hours of experience before understanding how to consistently outperform at scale.
cheevly
·2 bulan yang lalu·discuss
These types of comments help demonstrate first-hand how human reasoning stacks up against what an LLM would say in this situation.
cheevly
·2 bulan yang lalu·discuss
A lot of us have been doing this for over a year now.
cheevly
·2 bulan yang lalu·discuss
What would you even need to see? I struggle to find things that I cant do at scale with AI, and it’s dumbfounding to read posts about people that are unconvinced.