Launch HN: MinusX (YC S24) – AI assistant for data tools like Jupyter/Metabase
MinusX is a free Chrome extension that enhances data analysis in Jupyter and Metabase by automating interactions with AI, allowing users to explore data and ask questions. Future monetization may include subscriptions.
MinusX is a Chrome extension designed to enhance data analysis in Jupyter and Metabase by providing an AI assistant that interacts with these applications. The extension allows users to ask questions, explore data, and extend existing notebooks or dashboards through a simple interface. The creators, Vivek, Sreejith, and Arpit, aim to address common challenges faced by developers and product managers in accessing and analyzing data without needing to switch to new tools. Instead of building a new platform, MinusX retrofits existing analytics software, leveraging the capabilities of large language models (LLMs) to automate tasks like clicking and typing. The extension constructs a simplified representation of the host application's state and executes a sequence of actions based on user instructions. The team plans to open-source the extension and is considering a subscription model for future monetization. Currently, the product is free, and users can access a playground to test its features. The founders invite feedback and suggestions for additional tools to support.
- MinusX is a Chrome extension that enhances data analysis in Jupyter and Metabase.
- The extension automates interactions with analytics applications using AI, allowing users to ask questions and explore data.
- The creators focus on retrofitting existing tools rather than developing new platforms.
- The product is currently free, with plans for future monetization through subscriptions.
- The team is open to feedback and suggestions for additional tool support.
Related
Launch HN: Undermind (YC S24) – AI agent for discovering scientific papers
Josh and Tom are developing Undermind, a search engine for complex scientific research, using large language models to enhance search accuracy and comprehensiveness, inviting user feedback for improvements.
Using Agents to Not Use Agents: How we built our Text-to-SQL Q & A system
Ask-a-Metric is a WhatsApp-based AI tool for SQL queries in the development sector, improving accuracy and efficiency through a pseudo-agent pipeline, achieving under 15 seconds response time and low costs.
Building a Local Perplexity Alternative with Perplexica, Ollama, and SearXNG
The article outlines how to create a self-hosted alternative to the AI search engine Perplexity using open-source tools, emphasizing cost-effectiveness and customization through a step-by-step installation guide.
Launch HN: Synnax (YC S24) – Unified hardware control and sensor data streaming
Synnax is a platform that connects sensors and actuators for real-time telemetry and data analysis, featuring a scalable time series database, supporting multiple programming languages, and offering free usage for up to 50 channels.
Tell HN: X stopped requiring authentication, nitter works again
X has launched Grok 2, an AI assistant available through a premium subscription at $8/month, offering features like longer posts, video uploads, and reduced ads, enhancing user engagement.
- Users appreciate the integration with Metabase and the automation of data queries, expressing a desire for improved user experience.
- There are inquiries about the AI's capabilities, including model selection and performance on large datasets.
- Concerns about data privacy and clarity in data policies are prominent, with users seeking more information on how their data will be handled.
- Several users are curious about the underlying technology, specifically which language model is being utilized.
- Some users are interested in potential future developments, such as a Firefox extension and the possibility of competition from Metabase.
13 commentsIs there a way to select which model is being used? Anecdotally, I've found that Claude 3.5 Sonnet works incredibly well with even the most complex queries in one shot, which is not something I've seen with GPT-4o.
While this is clearly an ai analytics assistant your "retrofit" approach certainly differentiates you from existing approaches: https://github.com/Snowboard-Software/awesome-ai-analytics
Not quite sure if this should be a seperate category? It's more similar to the web automation agents like https://www.multion.ai/ than to https://www.getdot.ai/.
Anecdotally, my hardest problems w/ nl2sql are finding the right tables and adding the right filters.
Use case: Evidence-based policy; impact: https://en.wikipedia.org/wiki/Evidence-based_policy
Test case: "Find leading economic indicators like bond yield curve from discoverable datasets, and cache retrieved data like or with pandas-datareader"
Use case: Teach Applied ML, NNs, XAI: Explainable AI, and first ethics
Tools with integration opportunities:
Google Model Explorer: https://github.com/google-ai-edge/model-explorer
Yellowbrick ML; teaches ML concepts with Visualizers for humans working with scikit-learn, which can be used to ensemble LLMs and other NNs because of its Estimator interfaces : https://www.scikit-yb.org/en/latest/
Manim, ManimML, Blender, panda3d, unreal: "Explain this in 3d, with an interactive game"
Khanmigo; "Explain this to me with exercises"
"And Calculate cost of computation, and Identify relatively sustainable lower-cost methods for these computations"
"Identify where this process, these tools, and experts picking algos, hyperparameters, and parameters has introduced biases into the analysis, given input from additional agents"
How’s the performance on doing the same analysis on a dataset with 1 billion rows for instance?
Also does this work with self hosted Metabase or Metabase Cloud? Or both?
> We have nuanced privacy controls on minusx. Any data you share, which will be used to train better, more accurate models). We never share your data with third parties.
What are these nuanced controls? What data is used to train your models? Just column names and existing queries, or data from tables and query results as well that might be displayed on screen? Are your LLMs running entirely locally on your own hardware, and if not, how can you say the data is not shared with third parties? (EDIT: you mentioned GPT-4o in another comment so this statement cannot be correct.)
https://avanty.app/ is doing something similar in the Metabase space and has more clarity on their policies than you do.
Frankly, given the lack of care in your launch FAQs about privacy, it’s a hard ask to expect that you will treat customer data privacy with greater care. There is definitely a need for innovation in this space, but I’m unable to recommend or even test your product with this status quo.
Related
Launch HN: Undermind (YC S24) – AI agent for discovering scientific papers
Josh and Tom are developing Undermind, a search engine for complex scientific research, using large language models to enhance search accuracy and comprehensiveness, inviting user feedback for improvements.
Using Agents to Not Use Agents: How we built our Text-to-SQL Q & A system
Ask-a-Metric is a WhatsApp-based AI tool for SQL queries in the development sector, improving accuracy and efficiency through a pseudo-agent pipeline, achieving under 15 seconds response time and low costs.
Building a Local Perplexity Alternative with Perplexica, Ollama, and SearXNG
The article outlines how to create a self-hosted alternative to the AI search engine Perplexity using open-source tools, emphasizing cost-effectiveness and customization through a step-by-step installation guide.
Launch HN: Synnax (YC S24) – Unified hardware control and sensor data streaming
Synnax is a platform that connects sensors and actuators for real-time telemetry and data analysis, featuring a scalable time series database, supporting multiple programming languages, and offering free usage for up to 50 channels.
Tell HN: X stopped requiring authentication, nitter works again
X has launched Grok 2, an AI assistant available through a premium subscription at $8/month, offering features like longer posts, video uploads, and reduced ads, enhancing user engagement.