MENU

Edge

What happens when smart sensors move intelligence to the edge?

LEARN MORE

Data

How can publicly available data sources help us better understand the world we live in?

LEARN MORE

Trust

Are you sure your AI is doing what you think it’s doing?

LEARN MORE

MENU

Edge

What happens when smart sensors move intelligence to the edge?

LEARN MORE

Data

How can publicly available data sources help us better understand the world we live in?

LEARN MORE

Trust

Are you sure your AI is doing what you think it’s doing?

LEARN MORE

Understanding the World through the Open Source. Also, we break stuff. Sometimes. Proudly.
LEARN MORE ABOUT US

Explore With Us

See All
IQT Labs releases audit report of RoBERTa, an open source large language model

IQT Labs releases audit report of RoBERTa, an open source large language model

Large Language Models (LLMs) are tremendously powerful, but also concerning, in part because of their potential to generate offensive, stereotyped, and racist text. Since LLMs are trained on extremely large text datasets scraped from the Internet, it is difficult to…
Interrogating RoBERTa: A Case Study in Cybersecurity

Interrogating RoBERTa: A Case Study in Cybersecurity

Found It! How we discovered a security hole in a popular software actively used by millions of people around the world? This blog details an unexpected discovery in our audit of a Large Language Model released by Facebook.
Eating Every Last Slice of Your Raspberry Pi – GPU Offload on a Pi4

Eating Every Last Slice of Your Raspberry Pi – GPU Offload on a Pi4

IQT Labs has been experimenting using Raspberry Pi4s and Software Defined Radios (SDR) as an on-the-go platform, through the GamutRF project. Learn how we made GamutRF, running on a Pi4, more responsive and reliable by utilizing the built-in GPU to…
Saisiyat is where it is at! Auditing multi-lingual AI models

Saisiyat is where it is at! Auditing multi-lingual AI models

How do you audit an AI model and what can you expect to learn from it? This blog explores auditing multi-lingual AI models.
Interrogating RoBERTa: Inside the challenge of learning to audit AI models and tools

Interrogating RoBERTa: Inside the challenge of learning to audit AI models and tools

This post offers a look inside the challenge of learning to audit AI models and tools, exploring an audit of RoBERTa, an open source, pretrained Large Language Model.
IqtLabs
@IqtLabs

We asked VP of Operations Vishal Sandesara what trends he is seeing in 2023 ⬇️ #AI #MachineLearning https://t.co/rIb6FGPHVK

Read More »
09:00 PM · 27 Feb 2023
IqtLabs
@IqtLabs

The best way to get to know us is through our collaborative projects – both past and present – all of which reside in GitHub and are accessible to everyone. Check them out here:

Read More »
07:00 PM · 22 Feb 2023
IqtLabs
@IqtLabs

What does an AI system have in common with "Clever Hans," the horse mathematician and worldwide sensation circa 1904? AI tools sometimes fool us of their capabilities through misleading performances. Learn more on the blog: ...

Read More »
03:32 PM · 17 Feb 2023
IqtLabs
@IqtLabs

Join our team! We're #hiring a Systems Engineer to drive forward our focus on the application of emerging, #opensource technologies to national security mission challenges. https://t.co/QSnilFCYlc

Read More »
04:02 PM · 08 Feb 2023
IqtLabs
@IqtLabs

Check out our 3D printer making parts for our next project #DIY https://t.co/7TGyoeOoUT

Read More »
09:00 PM · 06 Feb 2023
IqtLabs
@IqtLabs

We're hiring a Machine Learning Engineer! Apply to join a team of builders applying emerging, open-source technologies to #NationalSecurity mission challenges: #opensource #engineering https://t.co/WCQEeUOB8R

Read More »
08:00 PM · 20 Jan 2023
IqtLabs
@IqtLabs

What if an #AI sought to explain itself to a human audience? SVP Andrea Brennen tells the story of ELIZA, the paperclip maximizer, which was recently published in @CircusBazaar:

Read More »
05:00 PM · 18 Jan 2023
IqtLabs
@IqtLabs

It's difficult to know how Large Language Models will perform in a specific context, or to anticipate undesirable biases in model output. Read more to learn about what happened during our AI audit report that focuses on a pretrained LLM cal...

Read More »
04:04 PM · 19 Dec 2022
IqtLabs
@IqtLabs

You can build your own version of something we created at IQT Labs with our GitHub Repos 💻 Check it out on our website and let us know how it goes!

Read More »
02:01 PM · 15 Dec 2022
IqtLabs
@IqtLabs

When it comes to software, one thing we know is that #AI and #MachineLearning can create new vulnerabilities. On this episode of The IQT Podcast, 3 of our colleagues explored AI Assurance and our #FakeFinder audit. #ICYMI ...

Read More »
04:01 PM · 09 Dec 2022

Get into the Weeds

Want to get even deeper into our work? Here are a few deep dives into how we break down problems into smaller pieces, pair applied research with the open-source platform, and highlight novel means to tackle some of the toughest problems.

AI Assurance Audit

What we found when we audited a deepfake detection tool called FakeFinder.

Synthesizing Robustness

Explores whether generative models can increase the utility of synthetic data for rare object detection.

Where in the World

Verifying the geographic location of outdoor images

About
Explore
Projects
Contact

Copyright © 2022 · IQT Labs LLC.  All Rights Reserved.

Twitter Github

Terms of Use | Privacy Policy

CLOSE
ABOUT
EXPLORE
EDGE
DATA
TRUST
PROJECTS
CONTACT

We use cookies to offer you a better experience. By continuing to use this website, you consent to the use of cookies in accordance with our Privacy Policy. Read More

Accept