Hacker News new | past | comments | ask | show | jobs | submit | more brylie's comments login

I’m building an app with OpenAI, using structured outputs. Does OpenAI also support prompt caching?


I'm sure internally they use it for the system prompt at least, probably since launch. And maybe for common initial user queries that exactly match.


They are certainly not passing the savings on to the users.


Yet. I suspect OpenAI will release a similar offering soon. (hooray, free market competition!)


That $100 billion data center has to get paid for somehow.


Not currently.


I’d really like a Notion that syncs to Git. Kind of like the original promise of GitBooks. Can TileDocs sync to Git/GitHub for team-based collaboration?


I’m currently working on GitHub integration. It’ll be ready soon. Stay tuned!


One use case is for retrieving similar documents, such as when recommending related content. Another use case is retrieving document segments that are similar to a user query and passing them along with the user query to a large language model for improvement in the generated response. Vector search is also better in some ways than keyword search since it can find documents that are semantically similar even when the user may not have used the exact keyword, or even partial keywords like “Postgres” instead of “PostgreSQL.”


Aiko, mentioned elsewhere, includes a local copy of the OpenAI Whisper model: https://apps.apple.com/app/aiko/id1672085276


Please remove the “74935 viewing “ from the beginning of the submission, since that is apparently a viewer count at the time of the HN posting.


Retrieval Augmented Generation uses text that is stored in a database to augment user prompts that are sent to a generative AI, like a large language model. The retrieval results are based on their similarities to the user input. The goal is to improve the output of the generative AI by providing more information in the input (user prompt + retrieval results.) For example, we can provide the LLM details from an internal knowledge base so it can generate responses that are specific to an organization rather than based on general information. It may also reduce errors and improve the relevancy of the model output, depending on the context.


I don’t know if it meets all of your criteria but SUSE might be an option:

https://www.suse.com/products/server/


I would gladly do that too if Claude supported voice-to-text prompting like Whisper.

I use ChatGPT around town and can’t always type easily. That and it is easier for me to speak stream-of-consciousness than slowly typing my thoughts. Typing is a significant bottleneck.


Whats your usage? The 'around town' triggered me to ask :)


All sorts of things.

I’m often thinking of ideas while walking or riding the bus. For example, I make plans for an English discussion group I’m facilitating while walking to the class. Or I’ll iterate on software project ideas as they come to mind, like creating design documents, GitHub issues, etc.

Another use case is for live translation where I speak English to ChatGPT and it translates the output to various languages. Then, I show the translation to the other person and let them speak their response for ChatGPT to translate. The interesting thing is somehow Whisper translates the foreign language back to English when it returns the transcribed text, so I don’t need to submit that text to ChatGPT. This live translation of spoken conversations is a really important feature particularly since I interact with many people with varying degree of English proficiency speaking many languages (namely, Russian, Suomi, Czech, and Farsi.)


Start with the customer needs rather than the technology. Do you have some specific product ideas? Those ideas would help steer technology decisions, particularly during the initial prototyping phase.


This is exactly what I was going to say, and PWA is like you're trying to build for 2 cycles ago.

When you've got the problem you want to work on, is a PWA the best method of use/distribution/discovery?

Perhaps a mobile app is the best method, or a hardware device.

When you're thinking about what you want to build, don't forget about distribution. There is a saying that 1st time founders focus on product, 2nd time founders focus on distribution.


What would be your top choice for a post-Git VCS and why? I’m interested to try alternatives.


I feel that to be qualified to answer your question I need to have used a non-git VCS on a non-trivial project. Which I haven't.

That said, jujutsu is the one that's most sparked my interest and seems most akin to the subset of git features that I use in my daily workflow. (In the way that everyone apparently uses a different subset of C++, I imagine everyone uses a different subset of git.)

This blogpost was what made me try it: https://v5.chriskrycho.com/essays/jj-init/ which I found from this recent HN thread https://news.ycombinator.com/item?id=39232456. Other HN threads about it: https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

That said, I haven't kept experimenting with it cause I had to stay productive (same reason I still haven't switched to Colemak). But I still have the tab open. And I did eventually switch to i3. So, maybe one day.


If your team is small, fossil is perfect.

https://fossil-scm.org/

(it's mentioned in the article)


I think fossil is not exactly post-git but runs in parallel with git. But definitely a good fit for small teams. For true post-git if you feel adventurous I would try jj or pijul.


I'm a happy git user, although I've heard great things about lazygit: https://github.com/jesseduffield/lazygit?tab=readme-ov-file


Yes I think for git users there are a number of great gui and tui and cli tools to simplify workflows. Here is a good list: https://github.com/dictcp/awesome-git?tab=readme-ov-file#cli...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: