The Thinking Machine

On the Thimblerig Game of “The Quality is 85%”: What’s Under This Thimble?

The Real Meaning of “Good Enough” in Translation and AI

Sep 29, 2025 • Logrus Global

1

The Snarl of GenAI: Evidence That Internal Entanglement Drives Mistakes

New research suggests AI’s biggest flaws aren’t bugs to be fixed, but a fundamental consequence of how they learn.

Sep 20, 2025 • Logrus Global

AI Content Labeling: Preparing for the New Compliance Baseline

We are now fully immersed in the age of AI-generated content.

Sep 15, 2025 • Logrus Global

June 2025

Hard fact: Automatic quality prediction based on neural models does NOT work at the segment level

Serge Gladkoff

Jun 19, 2025 • Logrus Global

5

January 2025

LLMs Continue to Hallucinate––and accurate measurement of how much exactly, reveals a stunning picture

When the first large language models (LLMs) emerged on the market, they amazed users with their fluency and breadth of knowledge.

Jan 29, 2025 • Logrus Global

4

1

The work of securing AI systems will never be complete: LLMs amplify existing security risks and introduce new ones

Although in late 2024 it seemed as if the AI and AGI hype was fading, the beginning of 2025 brought yet another wave of excitement after Sam Altman, the…

Jan 22, 2025 • Logrus Global

4

2

May 2024

A Thought Once Spoken Is a Lie

The Fundamental Reasons for Uncertainty and Low Inter-Rater Reliability on a Sentence Level

May 20, 2024 • Logrus Global

2

1

February 2024

Why you should not base your workflow process decisions on any segment-level score (including Phrase’s new QPS)

As I watched the recent video presentation of the Quality Performance Score (QPS) from Phrase with great interest, it raised some pertinent questions…

Feb 7, 2024 • Logrus Global

December 2023

Our Most Significant R&D Result in 2023: Edit Distance Prediction Method

As 2023 draws to a close, it’s a perfect time to talk about year-end results – and we have something very special up our sleeve.

Dec 18, 2023 • Logrus Global

November 2023

Why it is important to acknowledge the lack of intelligence in “AI”

The sooner we realize that AI’s output cannot be taken at face value without review, the sooner we understand the need for testing and quality…

Nov 21, 2023 • Logrus Global

October 2023

GEMBA-SQM translation quality evaluation is easy to implement as zero-shot LLM prompt … and totally useless

The hype ignores AI hallucination, because the hype is caused by people hallucinating on AI.

Oct 21, 2023 • Logrus Global

September 2023

Translation quality evaluation is all we need

It’s time to learn how to measure the quality of MT translation output correctly!

Sep 6, 2023