Close Menu
  • Home
  • AI
  • Art & Style
  • Economy
  • Entertainment
  • International
  • Market
  • Opinion
  • Politics
  • Sports
  • Trump
  • US
  • World
What's Hot

FBI announces thwarted alleged conspiracy targeting UFC event at White House

June 16, 2026

Pakistan moves to cut regular taxes following legal challenge from two young lawyers

June 16, 2026

Iran framework signed but not implemented

June 16, 2026
Facebook X (Twitter) Instagram
Smart Breaking News on AI, Business, Politics & Global Trends | WhistleBuzz
Facebook X (Twitter) Instagram
  • Home
  • AI
  • Art & Style
  • Economy
  • Entertainment
  • International
  • Market
  • Opinion
  • Politics
  • Sports
  • Trump
  • US
  • World
Smart Breaking News on AI, Business, Politics & Global Trends | WhistleBuzz
Home » Raise $9 million to build perhaps a more reliable kind of AI.
AI

Raise $9 million to build perhaps a more reliable kind of AI.

Editor-In-ChiefBy Editor-In-ChiefJune 16, 2026No Comments3 Mins Read
Share Facebook Twitter Pinterest LinkedIn Tumblr Telegram Email Copy Link
Follow Us
Google News Flipboard
Share
Facebook Twitter LinkedIn Pinterest Email


As LLM became more powerful, hallucinations proved stubbornly difficult to avoid. Even the smartest models will make errors. There are ways to detect these errors, but the industry is still figuring out the best methods.

Perhaps the company, which just raised $9 million in seed funding from Andreessen Horowitz, is trying to build a more rigorous method to spot these mistakes.

As stated by founder Peter Elias (pictured above), the company’s goal is to prevent hallucinations and simple factual errors from reaching users, and to achieve 99.99% accuracy, which is common in deterministic systems but much harder to achieve with AI. Ultimately, bringing LLM to that level of precision requires rethinking many of the fundamental assumptions of AI engineering.

Perhaps the company’s first product is a data science tool built to derive quick answers from complex datasets. Each result is accompanied by a citation and audit trail about how it was developed. This is an increasingly common technique among AI tools.

But preventing errors from creeping into these summaries required an elaborate harness system that Elias describes as a “data science mech suit.” The LLM’s first pass answers are checked against a deterministic validation system, and results that do not match the dataset are returned. Importantly, the LLM is trained on validators and the entire system is optimized for fast and accurate answers, the company said.

“What we learned building this is that the better the harness engineering, the weaker the model can be,” Elias says. “If you can adjust the context enough, the model doesn’t have to work as hard to do the right thing. Essentially, this is an exercise in reducing ambiguity.”

This will likely allow the company’s data science tools to run on significantly smaller AI models. Elias said the current version runs on a model that is “four classes weaker than the Frontier model,” which means it can run on local hardware (i.e., on desktop computers rather than in a data center), significantly reducing the token costs associated with using AI.

This is a welcome idea at a time when token costs are rising and many customers are rethinking their AI budgets. And Elias’ ideas go beyond data science. The same engine can be extended to cover use cases such as accounting and medical services (or, in Elias’s words, “any use case where accuracy is important”).

“I think it’s very interesting that no major AI lab has even tried this,” Elias says. “We are incentivized not to do that because the more times we modify the model, the more profitable it is.”

If you buy through links in our articles, we may earn a small commission. This does not affect editorial independence.



Source link

Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
Editor-In-Chief
  • Website

Related Posts

SpaceX to buy Cursor for $60 billion in stock, days after blockbuster IPO

June 16, 2026

Malaysian AI agent-powered messaging app Respond.io raises $62.5 million, eyes acquisition

June 16, 2026

Sundar Pichai faces boos and walkouts at Stanford University graduation ceremony over Google’s partnership with Israel and ICE

June 15, 2026
Add A Comment

Comments are closed.

News

What you need to know about this week’s US primaries | Election News

By Editor-In-ChiefJune 16, 2026

Voters will head to the polls this week in multiple states and the nation’s capital…

President Trump touts Iran deal and Ukraine ambitions at G7 attendance | Donald Trump News

June 15, 2026

It will take “months” for U.S. fuel prices to normalize after U.S.-Iran agreement to end war | U.S.-Israel war against Iran News

June 15, 2026
Top Trending

Raise $9 million to build perhaps a more reliable kind of AI.

By Editor-In-ChiefJune 16, 2026

As LLM became more powerful, hallucinations proved stubbornly difficult to avoid. Even…

SpaceX to buy Cursor for $60 billion in stock, days after blockbuster IPO

By Editor-In-ChiefJune 16, 2026

SpaceX has agreed to acquire AI coding startup Cursor in a $60…

Malaysian AI agent-powered messaging app Respond.io raises $62.5 million, eyes acquisition

By Editor-In-ChiefJune 16, 2026

In 2017, Respond.io set out to solve a simple problem: businesses couldn’t…

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Welcome to WhistleBuzz.com (“we,” “our,” or “us”). Your privacy is important to us. This Privacy Policy explains how we collect, use, disclose, and safeguard your information when you visit our website https://whistlebuzz.com/ (the “Site”). Please read this policy carefully to understand our views and practices regarding your personal data and how we will treat it.

Facebook X (Twitter) Instagram Pinterest YouTube

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Facebook X (Twitter) Instagram Pinterest
  • Home
  • Advertise With Us
  • Contact US
  • DMCA Policy
  • Privacy Policy
  • Terms & Conditions
  • About US
© 2026 whistlebuzz. Designed by whistlebuzz.

Type above and press Enter to search. Press Esc to cancel.