reframe VS mentat

NNext.ai » Software Engineer » Python » Full-time » NY, NY, USA » Remote

At [NNext.ai](http://NNext.ai) (read “Next.ai”), we are building building core infrastructure to simplify the process of building, deploying, and managing LLM-powered AI agents on tabular data, making it the most efficient solution available. NNext AI enables users to combine the power of Large Language Models (LLMs) like GPT with tools like the browser and Google Search, greatly increasing your productivity on workflows you once spent countless hours on. We are building a framework specialized for tabular data such as Spread sheets, Database Tables and CSVs, thereby taking advantage of the similarities and co-dependencies amongst data.

We are lean team of engineers looking for our first full time OSS contributor. Desirable experience includes distributed systems working with tools like Celery, Dash and Redis Streams. Visibility on Github is a huge plus. Show us previous OSS software you’ve contributed to or public personal projects with significant usage.

Website: https://nnext.ai

Github: https://github.com/nnextai/aigent

Email: [email protected]

https://github.com/nnextdb/nnext/blob/main/FAQs.md Q: How does this differ from Faiss, ScaNN and Annoy?

What’s NNext? [Say “Next”] NNextDB is a blazingly fast ⚡️, open-source 📖, (vector) neural search 🔎 engine for building delightful AI Apps 🦾. Github: https://github.com/nnextdb/nnext Like what you see? Please give us a Star 🤩. Applications Vector search is a key concept in modern machine learning systems. It’s the technology behind

These things mostly work by having some vision model, chopping it off somewhere in the middle and using that layer as an "embedding" for your image. Then you look for images that have embeddings which are close together (normally in the sense of Euclidean distance, e.g.)

Code Link: https://github.com/nnextdb/nnext

NNextDB - a blazing fast, open source, vector search database for building AP applications.

https://github.com/nnextdb/nnext

Hey Paul, I'm a Mentat author.

> I also notice that the instructions prompt that mentat uses seems to be inspired by the aider benchmark? Glad to see others adopting similar benchmarking approaches.

We were inspired by you to use Exercism as a benchmark, thank you! We will add attribution for that. We switched our original instruction prompts for that benchmark to be similar to Aiders to allow for fair comparison.

> After looking around a bit, there seems to be a bunch of aider code in your repo. Some attribution would be appreciated.

We have an unused implementation of your output response format (https://github.com/AbanteAI/mentat/blob/main/mentat/parsers/...), but I don't know what else you are seeing? We implemented that to compare with our response formats and didn't find much difference in performance.

Abante AI | Full-time | Senior Software Engineer | Remote or Hybrid SF Bay Area

Abante AI is a new startup building Mentat, an open source, GPT-4 powered coding assistant. Mentat runs on the command line, gathering project context and coordinating edits across multiple files: https://github.com/biobootloader/mentat

- work with a small, talented team on an ambitious project

- open source: share what you build

- apply research to make a real product

- competitive pay + early equity

Contact me: [email protected]