HN user

Pr0ject217

168 karma
Posts1
Comments177
View on HN
Googlebook 2 months ago

In practice I find the Gemini models to be the worst for coding and design.

Laws of UX 3 months ago

The irony is that the design and UX of the website is terrible.

GPT-4o 2 years ago

"OpenAI is still working in GPT-4-level models."

This may or may not be true - just because we haven't seen GPT-level-5 capabilities, does not mean that it does not yet exist. It is highly unlikely that what they ship is actually the full capability of what they have access to.

"Which would be at odds with sending data up to the cloud for processing"

I don't think there is enough information here for that to be a true claim - it is possible to send the input used for inference, to the cloud, while computing the result locally. It is also possible to store the input used for inference while offline, and send that later when the device is online.

Speaking from personal experience, I moved from VSCode to Doom Emacs a year ago, and the on-ramp wasn't nearly long or as tough as I thought. The defaults are good, and anything else that I customized I actually just used ChatGPT/GPT-4 to generate it. It took about a month to get used to the new setup. With LSP/Magit, it feels like I'm not missing out on much from what VSCode offered, and then whenever I want to personalize it, I can. For a creative person (which I'd argue most developers are, kind of by definition), it's fun.

I agree. When possible/working with sound, I would take a tactile experience (right-brain/feel?) over a mathematical/analytical experience (left-brain/logic?). I also don't know music theory and I haven't dedicated time to learn math, so I lean on my intuition more than anything.