Show HN: A magic frame you can prompt to show generated art to an e-ink display https://ift.tt/yBHiuRV

Show HN: A magic frame you can prompt to show generated art to an e-ink display https://ift.tt/7pE6sc2 December 17, 2022 at 09:41AM

Show HN: Simply see your client hints sent by Chrome https://ift.tt/90MFbs5

Show HN: Simply see your client hints sent by Chrome Chrome will start to reduce the UserAgent string and replace it with client hints. here you can simply see your current UA, the reduced one, and your client hints. https://clienthints.me/ December 17, 2022 at 08:34AM

Show HN: I made a Slack bot that qualifies your sign-ups using GPT-3 https://ift.tt/zxpafUt

Show HN: I made a Slack bot that qualifies your sign-ups using GPT-3 OP here, this was super fun to build. It all started from playing around with Nat Friedman's GPT browser https://twitter.com/0xferruccio/status/1599014988693180417 Then after having this running for our product for a couple of days or so we decided to give 10 customers access and they loved it! So expanding access now feels great :) https://ift.tt/xseKY1r December 15, 2022 at 09:00PM

Show HN: The easiest way to run a brainstorm, supercharged with A.I https://ift.tt/TZW5bON

Show HN: The easiest way to run a brainstorm, supercharged with A.I Hello friends! We've been working hard on building Mimosa, and would love for you to try it! No signups required. Facilitating brainstorming sessions can be a challenging and time-consuming task. It's difficult to keep everyone on agenda, engaged, and contributing. So we've built Mimosa to be the easiest way to facilitate a brainstorming session. Imagine if a "digital whiteboard" and a "trello board" had a baby, but built with all the best practices of professional facilitation. With Mimosa, you can minimize bias by allowing team members to contribute anonymously before revealing their ideas. This ensures that everyone has a fair chance to share their thoughts and ideas without fear of judgment. Once the brainstorming session is complete, you can easily view and export the final results. This allows you to keep track of a meeting's effectiveness and share it with stakeholders. But the real game-changer is our AI Brainstorming features and it's ability to turn your 1x team into a 10x team. It help generates and collaborates with you in your brainstorming session to help you come up with more and better ideas. We're both scared and excited to hear all your thoughts, HN! :) Please do let us know any features or improvements you think we should make to help you in your meetings. https://mimosa.so/ December 17, 2022 at 12:11AM

Show HN: Simpler – Your GPT-3 Task Planner https://ift.tt/zuFbxkS

Show HN: Simpler – Your GPT-3 Task Planner https://simplerlist.com December 16, 2022 at 07:11AM

Show HN: I'm challenging your clicking speed with this game I rebuilt https://ift.tt/teBz9hs

Show HN: I'm challenging your clicking speed with this game I rebuilt https://ift.tt/80nxWYD December 16, 2022 at 02:15AM

Show HN: Natural language Twitter search using Codex https://ift.tt/P5spM2a

Show HN: Natural language Twitter search using Codex We built a structured search engine for Twitter called Bird SQL, available at https://ift.tt/g1p29Gd . 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/GDk7Ieq https://ift.tt/ByEcuSL December 16, 2022 at 03:42AM