Regardless, if we stick with the example of the Zig docs, using the search and then opening the actual docs is a much better and faster experience for me. I get the context I need, I don’t get the verbose llm output that packages it and I get there faster.

Mind you, I use AI a lot and have subscriptions to all of the major models, but this is just not a use-case I find useful in my workflow.

I also keep trying to use it this way by looking for things such as decent libraries or frameworks for something new im trying out. I’d say that at least 50% of the time I end up searching for myself and finding popular ones that were completely ignored by whatever LLM I searched with. Always a frustrating experience…

https://news.ycombinator.com/item?id=48269481

By “their own index” i assume you mean training data? If so, thats a big part of the issue for me. As an example, if I ask an LLM for some part of the Zig stdlib, I will get an incorrect answer 10/10 times because it will refuse to look up the latest documentation.

Looking through some of my history of today:

- “github rate-limits”

- “oriental hornet”

- “riva 88 florida”

- “logistic map”

- “zeiss euv mirror”

- “authentik helm”

Just to name a few…

For a lot of these, LLMs would slow me down significantly. Most of the time I already know exactly what im looking for.

Search is always faster than asking an LLM if I have a general idea of what I am looking for. I may consult an LLM if I want to compare things or kick off deep research, but most of the time I find myself having to go back and forth with it and correcting assumptions it made.

According to my Kagi stats, I am averaging around 3k searches per month.

I can’t help but feel that you are really missing out on a lot of results when just relying on LLMs for search.

HDMI 2.0, USB-A, Wifi-6E, BT 5.3. This is a legacy device.

LiteLLM proxy also adds quite some overhead as well.

I have personally settled on a mix of Bifrost as my router which connects to OpenRouter or some other providers that I deem more privacy friendly.

Comments URL: https://news.ycombinator.com/item?id=47493049

Points: 3

# Comments: 0

I am merely commenting on your takeaway that this somehow means that some cultures see schizophrenia as "friendly", which does absolutely does not follow from the fact that the "mostly, the voices are good".

I would also think that this is likely due to cultural differences and in many cases probably adds to the problem.

https://doi.org/10.3109/09540261.2012.711746

From the full Article:

"People suffering from psychotic illness continue to hold multi-explanatory models. The cultural, religious and social explanatory models are predominant in non-western cultures."

"Limited evidence suggests that traditional belief models affect [duration of untreated psychosis], and explanatory models based on spiritual and social causes of illness may result in delayed presentations for professional help."

That should not be your conclusion from the article.

"the voices" are hardly the only symptom that people with schizophrenia suffer from. A lot of those affected don't have auditory hallucinations at all and are still suffering from one of the (if not the) most debilitating mental disorders out there.

Calling it "friendly" risks trivialising of the very real symptoms.

Ruff isn’t stable yet either and has evolved into the de facto standard for new projects. It has more than double the amount of rules than Pylint does. Also downloaded more than 3 times as often as Pylint in the past month.

Pylint has some advantages, sure, but Ruffs adoption speaks for itself. Pylint is 25 years old. You’d hope they do some things better.

Saying that uv is their only winner is a hilarious take.

Macbook Neo is also 219ppi vs Surface Laptop at 178ppi. We’ll see about performance, but i’d expect the macbook to be on par or better.