Important initiave
HN user
Xeophon
I love espanso. I live it over AHK as it doesn't have some obscure and hard to learn language, so I can just write some python scripts and trigger them with espanso.
It’s pretty interesting to see both companies copying each other. Bing Chat has GPT4 with Vision, Chat History and some other goodies whereas OpenAI extends towards B2B.
Kagi has such a feature, its called Universal Summarizer [0]
[0] https://kagi.com/summarizer/index.html?url=https%3A%2F%2Fwww...
Related work is the planning paper by Valmeekan et al [1]. The gist is that LLMs are incapable of planning, which is due to their autoregressive nature. METAs Head of AI Yann Lecun also talks about this topic in a talk [2]. As RT2 is based on a similar architecture, I think the results will be similar.
[1] https://arxiv.org/abs/2305.15771 [2] https://youtu.be/x10964w00zk
Isn't Insomnia the same? The parent company (KongHQ) is also backed by VCs @ 1.2B valuation. Whats the difference/better?
I am a beta user and I am seriously impressed if I’m being honest. It works fully offline, is multilingual and is fast, even on the non-latest iPhone (I am using an iPhone 12 Pro Max). It is way better than apples previous version and better than locally installed whisper. They’ve done incredible work. Same with the new, transformer-based keyboard on iOS which is way better. And if you type in English, it sometimes shows word suggestions in the text field itself (similar how copilot works in an IDE).
There are already some instances which are defederating, see [0] for a write-up
[0] https://daringfireball.net/2023/06/more_on_preemptively_bloc...
Russian-run sites like RT are banned through the whole EU. However, such spikes cannot be seen in other EU countries such as France.
I recently re-subbed after I noticed that they increased their monthly cap for searches.
An investment round is interesting—on the one hand, it will keep them afloat, while on the other hand it means that the investors want to see returns one day and this money has to come from somewhere.
Popular examples are Weaviate and Qdrant
You are looking for https://typeset.io/
Sadly they do not seem to have all the papers. ArXiV is missing completely, e.g. searching for „Attention is all you need“ does not return the paper which has been published on NeurIPS
Recently discovered grep.app and it is incredibly useful. Wish I’ve knew it earlier.
Im on the opposite site: Currently, I do not use Kagi. Such features would convince me to switch (and therefore, pay).
However, you can run Stable Diffusion on your hardware, same as Whisper etc.
Kotlin is simply amazing if you pair it with the corresponding frameworks, i.e. kotlinx serialization instead of gson/jackson etc. Quickly fell in love with the language and Java, even in the new(er) versions, feels outdated.
OP mentions GPT in concert with WolframAlpha, which has already been implemented[0], showing a symbiosis between generation of text with proven knowledge.
But one timer and one timer only. Siri cannot start a second timer on your phone in 2023. Its ridiculous
One has to bow first and I do not think that journals and large publishers will be the ones. A typst <-> LaTeX converter would be something which would be a huge feature I'd pay for. I am writing papers for journals/publishers after all.
Check out SciSpace [0], it was trained specifically for this and even has a function to explain formulas, algorithms and tables on top of explaining general questions about the paper or paragraphs. It’s amazing and is now an integral part of my workflow. At first, I upload the paper to SciSpace, ask it some general questions about the paper and then read it more throughly. If some things are confusing, I mark them and let the AI explain them. It’s kind-blowing and completely free.
Isn’t this the same as replying to ChatGPT in the same conversation?
The „news“, especially in finance, is more and more autogenerated these days
At this point it’s just a matter of time until someone does an extension for all browsers.