Launch HN: Mentat (YC S16) – Controlling LLMs with Runtime Intervention

Published: 1 month ago (December 9, 2025 at 11:37 AM EST)

1 min read

Source: Hacker News

Overview

Hi HN, I’m Cyril from CTGT. Today we’re launching Mentat (https://api.ctgt.ai/v1/chat/completions), an API that gives developers deterministic control over LLM behavior, steering reasoning and removing bias on the fly, without the compute of fine‑tuning or the brittleness of prompt engineering. We u…

Back to Blog

Launch HN: Mentat (YC F24) – Controlling LLMs with Runtime Intervention

Hi HN, I’m Cyril from CTGT. Today we’re launching Mentat https://docs.ctgt.ai/api-reference/endpoint/chat-completions, an API that gives developers deterministi...

Guardrail your LLMs

!Forem Logohttps://media2.dev.to/dynamic/image/width=65,height=,fit=scale-down,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%...

Anthropic Skills. The Landscape for New Models and Architecture

!Cover image for Anthropic Skills. The Landscape for New Models and Architecturehttps://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto...

From Prompts to Action: My Journey Through the Google & Kaggle AI Agents Bootcamp

From Prompts to Action: My Journey Through the Google & Kaggle AI Agents Bootcamp This is a submission for the Google AI Agents Writing Challengehttps://dev.to...

Overview

Related posts

Launch HN: Mentat (YC F24) – Controlling LLMs with Runtime Intervention

Guardrail your LLMs

Anthropic Skills. The Landscape for New Models and Architecture

From Prompts to Action: My Journey Through the Google & Kaggle AI Agents Bootcamp