In my opinion we need a multi-modal model that is great at both tabular datasets and text analysis. Most analytical work in economics, policy, public health, medicine etc requires a combination of crosschecking between both. Current gen LLMs are not good enough at generating novel insights by looking at tables and text at the same time. I also haven’t have found any data on this so please serve it to be on a plate if I’m wrong.

Stina keeps all conversation history and data in localstorage on the browser, which is great when your manager asks you about data security considerations of AI chatbots.

Stina is a client-side solution that requires no server, no installations, and no build tools. Written in vanilla javascript with all dependencies bundled. This enables editing the code in environments where there is no access to Node.js, NPM or other JS-build tools.

Right now it supports Azure AI Foundry deployments, OpenAIs API, Anthropic and Ollama.

Stina can be hosted on a SharePoint server, run directly from the filesystem, or accessed through a local web server. It supports multiple language models, custom instructions, and dynamic system prompts.

I built this for my own needs at work where we have access to API keys to an Azure AI Foundry sandbox on the company tenant. By renaming chat.html to chat.aspx and putting the repo in a folder on SharePoint, I can run this as a chatbot internally.

If you want to contribute, you are very welcome to do so. I would love to extend this with the ability to chat to files, and perhaps even add an in-memory clientside vector database support to allow doing lightweight clientside RAG on documents accessible with the filesystem.

Comments URL: https://news.ycombinator.com/item?id=42714746

Points: 4

# Comments: 0

I needed a project management tool, and what we had on offer was too clunky and old. I built SimpleGantt to be ultra lightweight and portable. It's one HTML, one Javascript and one CSS file. Each project is saved into a single .yaml file.

If you have a SharePoint environment you can "host" it by uploading the repo to SharePoint after renaming simplegantt.html to simplegantt.aspx. That allows anyone with access to open the tool by simply having the URL.

Try it at: https://aerugo.github.io/simplegantt/simplegantt

This is a couple of days of tinkering, and mostly exists to keep me from going crazy while managing projects with lots of deadlines and dependencies, so don't expect much. But another person in the same position, finding this might lead to calmer days.

Comments URL: https://news.ycombinator.com/item?id=42647668

Points: 115

# Comments: 29

Suppose there are three co-founders looking for a problem to solve. Suppose we want to start a business that makes a positive impact on the world. Suppose we have expertise and experience in the following areas: Web development, applications of AI and ML, data science and analytics, product management, e-commerce, direct-to-consumer product development and sales, blockchain technologies, community engagement, personal development and leadership. Educational background from top-tier engineering school in automation, biotechnology, and business development.

I'm looking for ideas to fall in love with. If you have one you want to share, I would be incredibly grateful.

Comments URL: https://news.ycombinator.com/item?id=41169411

Points: 2

# Comments: 2

New release https://github.com/aerugo/prelude/releases/tag/v0.3 and pushed to the Homebrew formula

However, I just had a go at using Aider, and WOW - I have tried a bunch of these auto-commit tools before (GPT Engineer, Fume, etc) but I found them to be clunky and unintuitive. Aider has fixed a lot of these problems, and I absolutely love it. Can't believe I hadn't heard of it until now. Thanks! I see myself using this quite a bit, and using Prelude when I need to debug something where the Aider workflow gets stuck.

——

I want to add a feature to my Content.js component. In the table that displays names of animals, I want to add an Edit button in a new column on each row. When clicked, it should bring up a modal that allows me to edit the name and emoji of the animal.

Review my codebase to see how CRUD actions are implemented for other features. Make sure you follow the established code patterns in the project.

Before starting to code, consider best practices for UX of a feature like this and make sure the implementation is user friendly and follows best practices.

After reviewing the code, describe how you will implement the feature make a plan for how to implement. After that, write the complete code for the implementation.

As for multiple stages, it means the tool itself is doing a few calls to the model. What do the code summaries look like? Just function and class doctrings? Getting the model to write summaries that are comprehensive enough to guide development but still more compact than the code itself seems like it may not be a trivial problem.

Prelude is rather meant for when you are pair-programming with a chat model and find yourself pasting a lot of context to remind the model of the state of your code. I always have terminals open anyway, so having it as a CLI tool rather than needing to make requests to a server, makes sense for me.

--- File: ~/GitRepos/kanot/prelude ---

Prelude is meant to really just do a single thing. I haven’t felt the need for things like templates, but I will give code2prompt a spin if I need more fancy things.