Chrome addon to lookup selected text via ChatGPT using custom prompts
Made this (GPT-4 made this actually) for myself mainly to do quick lookups on selected text. Add your api key and then your own system prompts in options. Then from context menu send selected text to ChatGPT with one of your prompts. Result should appear on top of page. I haven't looked much into publishing this on store yet, might do that later. At the moment, you have to load this in Developer mode via Load Unpacked button on extensions page in chrome. Tip: if you have only one prompt enabled, context menu will not be nested.
In plain words
This Chrome extension allows users to quickly look up selected text by sending it to ChatGPT with custom prompts. After adding an API key and configuring system prompts in the options menu, users can right-click any selected text to query ChatGPT via the context menu, with results displayed at the top of the page. Currently requires manual installation in Chrome's developer mode. The tool is designed for users who frequently need to perform quick text lookups and customization.
written from the facts on this page · September 2026
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, November 2023
the whole month →
Discover & book top creators to promote your product
Growth · 2023 · passionfroot.me
