Fastino Labs Releases GLiDE Decision Model With Adaptive Reasoning

Oct 2, 2026
GLiDE selects actions from predefined options and applies additional reasoning when its initial confidence is low. Fastino says the model scored 64.81 on Decision Index version 0.2.1.

Fastino Labs announces GLiDE in a press release, describing it as a decision model that applies adaptive reasoning when confidence is low. The model is available through the Fastino API under the model ID fastino/GLiDE.

GLiDE receives an application's current state and a defined set of options. It returns a selected action, a confidence score and a probability for each option. Fastino says about two thirds of test requests used a fast initial pass, while the remaining requests received additional reasoning. The model supports a context window of 40,000 tokens.

Fastino reports a score of 64.81 on Decision Index version 0.2.1, compared with 57.91 for TypeSafe AI's Jev decision model. GLiDE scored higher across all five evaluation areas and on 31 of 38 benchmarks. These results come from Fastino's own run of the official evaluation harness across 155,390 requests.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.