back
user profile
helloplanets
2,648karma·541submissions·September 15, 2020
recent activity (541 total)
comment
No wonder it extrapolated into the asshole dimension based on prompt excerpt tbh...
comment
> The Beatles wrote 227 songs, but only 34 hit the Top 10. Do you think they would put out a song that they didn't believe could be a hit? Mozart wrote over 600 songs, but only about 50 of the…
comment
The most important part is to just pay attention to how your current setup affects your mood, creativity, focus, etc. It'll be way easier to adjust once you're in tune with that. It's…
comment
Specifics on the setup. Specifics on the projects. SHOW ME THE MONEY!!!
comment
We need more of these kinds of tightly time controlled challenges for LLMs.
comment
Isn't this exactly the point the original post is making?
comment
Honestly thought this was some sort of satire on corporate ass-kissing at first.
comment
Why is this flagged?
comment
For the visual learners, here's a classic intro to how LLMs work: https://bbycroft.net/llm
comment
Even if you turn the temperature down to 0, it's not deterministic. Floating points are messy. If there is even a tiny difference when it comes to the order of operations on the actual GPU that…
comment
This guy is literally smirking while talking about this. It's like he's proud of himself for being able to produce doublespeak so effectively.
comment
He wasn't saying that both of the models suck, but that the heuristics for measuring model capability suck
comment
> Let's say your organization wants to add "dark mode" to your site. How does that happen? A site-wide feature usually requires several people to hash out the concerns and explore co…
comment
China is not just one company... And Google has been recently putting out more than any one of them AFAIK.
comment
The tortoise metaphor doesn't really fit for Google's current AI pace. They've been shipping more than any other company in the field for the last year.
comment
And when programming with agentic tools, you need to actively push for the idea to not regress to the most obvious/average version. The amount of effort you need to expend on pushing the idea tha…