back
user profile
helloplanets
2,649karma·541submissions·September 15, 2020
recent activity (541 total)
comment
Are you using a tool other than ChatGPT? If so, check the full prompt that's being sent. It can sometimes kneecap the model. Tools having slightly unsuitable built in prompts/context sometim…
comment
Source?
comment
It's not a model of text, though. It's a model of multiple types of data. Pretty much all modern models are multimodal.
comment
A lot of people make small games just for fun, like any other creative hobby. Similar to: Making music, writing, drawing, 3d modeling, etc. Actually, you can put all of those together and use them in …
comment
He addressed your point in the paragraph before that. The paragraph from which you quoted was meant to show the difference between your point and the fact that the original research was indeed measuri…
comment
Here's a couple examples:
https://lucumr.pocoo.org/2025/6/21/my-first-ai-library/
https://www.indragie.com/blog/i-shipped-a-macos-app-bui…
comment
That's a strange comparison! I guess this is where the ultimate caricature of cool comes from, though: Sex, drugs and rock 'n' roll -> Hedonistic, powerful and adventurous. Crank tho…
comment
Yep, it's not as far fetched as it would've been a year ago. A scenario where you're running an agent in 'yolo mode', it opening up some poisonous readme / docs / pa…
comment
True, it can't be saved from that at all. But it can still automatically keep a log of the whole process, instead of you having to do it manually, so it's easier to keep track what's go…
comment
PSA: This is by AE Studio, which is a company that sells AI alignment services. [0] To be honest, all of their sites having a 'vibe coded' look feels a bit off given the context. Making clai…
comment
How does this result in less accountability, if for the AI agent to even have a chance to work properly it would basically need to save all of the calls, emails and other information in a persistent w…
comment
I'm actually surprised the sort of sludge described in the article isn't already illegal.
comment
> the current models already cost something on the line of the median country GDP to train This is just blatantly false. > According to AI Index estimates, the training costs of state-of-the-art…
comment
All completely true. But I also wouldn't voluntarily run a marathon in tennis shoes.
comment
How does this differ from function calling? For example, the basic enums example for Gemini function calling: > color_temp: {
type: Type.STRING,
enum: ['daylight', 'c…
comment
It would be completely disrespectful to call it Miyazaki's. It's absolutely not. If you sample a Stevie Wonder song, you can't call yourself Stevie Wonder. Everyone knows who Stevie Won…
comment
That's rough. And somehow reeks like it's inspired by that old clip of Miyazaki trashing the procedurally generated 'monster' animation. You're intentionally misinterpreting w…
comment
Touch screens (especially tablets) are also great for bullet because you can just tap-tap move, with as many fingers as you like! Small unrelated nit: It's Elo rating instead of ELO, as Elo just …
comment
I absolutely believe inference is cheap and efficient, but the net impact of training the model should be also added to the equation. Not just the cost of inference. Is this information readily availa…
comment
They definitely do strain the neurology and thinking metaphors in that article. But the Dijkstra's algorithm and A* comparisons are the flipside of that same coin. They aren't trying to make…
comment
What's your take on Anthropic's 'Tracing the thoughts of a large language model'? [0] > To write the second line, the model had to satisfy two constraints at the same time: the …
comment
Is there a good chart somewhere, to compare all the current AI coding CLIs / IDEs / extensions with one another?