Licklider launches SciGround to verify AI-assisted research
Tokyo startup Licklider has launched SciGround, a tool that checks the statistics behind AI-assisted research outside the language model, the company announced. Researchers keep using their own AI assistant, which calls SciGround through the Model Context Protocol; the MCP connector is in public beta.
SciGround runs checks in established software such as SciPy, R and the Z3 solver, requires the test design to be fixed before any result is shown, and refuses rather than approximates when data do not fit. Each result comes with a record of assumptions, inputs and software versions so others can repeat it. At launch it supports common tests including t-tests, ANOVA and RNA-seq differential expression.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.
Also, consider following us on social media:
AI Programming Weekly
Weekly news about AI tools for software engineers, AI enabled IDE's and much more.
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
OpenAI Introduces BioBasicsBench for Wet Lab Analysis
Tessa AI Launches Free Tool to Check Health News Research
Google Opens AI Tools for STEM Simulations and Document Review
AlphaLab launches Quanty One, an AI quant researcher
Shanghai AI Laboratory releases Sage-A1.5 for scientific agents
Daily AI Brief: the AI news that matters, in your inbox.