342
Productivity & Workflow347
Automation & Workflow240
Software Development244
Marketing & Growth200
AI Infrastructure & MLOps191
Photography & Imaging155
Writing & Content Creation194
Design & Creative170
Data & Analytics166
Customer Support152
Education & Learning136
Sales & Outreach129
Voice & Speech130
Operations & Admin119
The startup says its new tool can flag natural and AI-designed germs using a laptop and a USB gene sequencer, even without an internet connection.
In short: Radical Numerics says it built an AI tool that can help flag dangerous germs, including ones designed with AI, using a laptop and a small gene-reading device.
Radical Numerics announced a new product called Omnii Defense. The company says it can analyze genetic material from a pathogen (a germ that can cause disease) using a laptop and a USB gene sequencer, which is a small device that reads DNA like a scanner reads a barcode.
A key point is that Omnii Defense can run without an internet connection. Radical Numerics says this could help researchers who work in places where service is unreliable, like field sites during an outbreak.
Omnii Defense makes several guesses from a genetic sequence, including whether the organism is likely to be harmful and whether the sequence looks unnatural or possibly AI-generated. It then produces a “threat score” from 0 to 1, where a higher number suggests higher concern.
The company says older tools often work by matching a sequence to a library of known organisms, like looking for an exact book in a catalog. By contrast, Omnii Defense aims to spot patterns that still look risky even if the genetic “spelling” has been changed.
Radical Numerics says access is currently limited to vetted external testers. It is working with national labs, government agencies, and other evaluators to check how well the tool performs.
AI labs have warned that powerful AI could make it easier for bad actors to design bioweapons, even if many scientists consider that unlikely. Tools that help quickly flag suspicious samples could support public health teams by pointing them to what needs a closer look, especially when time and connectivity are limited.
Source: Wired