Show HN: Natural language Twitter search using Codex We built a structured search engine for Twitter called Bird SQL, available at https://ift.tt/zZsLdoU . Our search interface uses OpenAI Codex to translate natural language to SQL. Our backend then verifies the SQL, executes it, and displays the results on the web app. This makes large structured datasets like a scrape of Twitter easy for anyone to explore. As background, while working on text-to-SQL as a general problem, we came to believe one of its most powerful applications is as a search tool because: - SQL is hard to write by hand and prone to errors - It allows you to iterate quickly if you’re exploring a new dataset - A lot of contextual information that you’d normally have to internalize (e.g. your data’s schema) can be automatically generated and offloaded to the language model Using large language models (LLMs) like Codex to write the SQL for you means you don’t have to worry about the nitty gritty language details, but still benefit from the power of a language like SQL. Also, after seeing the results of the query, you can inspect (and if necessary, change) the SQL. The lack of this sort of explainability of the query result is one of the more notorious challenges of returning the output of an LLM directly to the user. Additionally, using LLMs in this way makes these kinds of queries over structured data accessible to people who know little or no SQL. While Bird SQL shares significant infrastructure with our more general LLM-powered search engine over unstructured data (Ask Perplexity - https://perplexity.ai[1] ), the two approaches and their respective challenges are quite different. For example, the type of models are different (GPT3.5 vs Codex), obviously the model prompts have different structure, and how to verify model output when its text vs when its code is different. We are currently exploring ways to combine the two approaches, such as using the results of retrieving information from a structured source (as in Bird SQL) as one of the inputs for the LLM to interpret or summarize (as in Ask Perplexity). We would love to hear your questions, suggestions, and feedback! [1] https://ift.tt/dpzN7Z5 https://ift.tt/fgkWEDO December 16, 2022 at 04:12AM
Show HN: Tape It, iOS recording app for musicians Hello HN, Over the last 15 months, two friends and I developed the music recording app we felt we wanted based on our own needs as musicians. It's called Tape It [1] and has just recently hit the Apple App Store [2]. We put a lot of effort into a good UX to help musicians really focus on playing their instrument instead of pretending to be a recording engineer. The app records in stereo on newer iPhones (although that's a premium feature; the free version only records in standard mono audio quality). I would be really grateful for advice from this community on how to best approach marketing. We had a great TechCrunch article covering our launch [3], and we posted it on various music websites. Turns out advertising on Google or Apple Search is a dark art, though. We have some good ideas for developing a good social media presence, but they will take time. Please hit us with feedback, opinions and advice that you think a young ind...
Comments