GLiDE by Fastino Labs: A Post-Trainable Reasoning Decision Model
Melvin Vivas · X video post · 2026-10-02 · 0:38 · 175 views · Open on X
Topics: LLM Fundamentals, Fine-tuning & Model Customization, Industry Trends & Job Market · Level: intermediate
Summary
Melvin Vivas shares Fastino Labs' launch of GLiDE, a "thinking decision model" for decisions that need a lot of reasoning. He compares it to the decision model Jev and points out that, unlike Jev, GLiDE can be post-trained. The quoted launch post claims GLiDE beats Jev on the official Decision Index 0.2.1 scorer. The video has no usable speech; the transcript is only a captioning artifact.
Key points
- GLiDE is a new 'thinking decision model' from Fastino Labs (@fastinoAI), built for decisions that need a lot of reasoning.
- Main difference the creator points out: unlike Jev, GLiDE lets you post-train (customize) the model.
- On the official Decision Index 0.2.1 scorer, GLiDE scores 64.81, which Fastino says is 6.90 skill points ahead of Jev.
- Fastino says GLiDE beats Jev in all five evaluation areas, including one with an 11.5-point lead (the post is cut off before naming it).
- All benchmark numbers come from the vendor's launch post. Check them yourself before relying on them.
Resources mentioned
- Fastino Labs (@fastinoAI) on X · person · x.com · free
The X account of Fastino Labs, which builds GLiNER decision models and shares demos.
Also in: GLiDE: Fastino's Decision Model with Adaptive Thinking (Melvin Vivas on X · notes), GLiNER decision model demos from Fastino Labs (Melvin Vivas on X · notes), AIBackends v0.8.1 adds GLiNER2.5-Decide local classification (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes) and 4 more - GLiDE · tool · fastino.ai · check price
Fastino Labs' decision model, which uses adaptive thinking (fast probabilities first, reasoning only when uncertain).
Also in: GLiDE: Fastino's Decision Model with Adaptive Thinking (Melvin Vivas on X · notes) - Jev · tool · typesafe.ai · paid
A decision model that makes turn-level forecasts on AI agent conversations using only structural signals (turns, tool calls, workflow stages, timing).
Also in: MLflow 3.17.0: Jev models as LLM judges in GenAI evaluate (Melvin Vivas on X · notes), JevDev v0.1.3: Free UI Environment for Experimenting with Jev Models (Melvin Vivas on X · notes), Automating Insurance Receipt Claims with OCR and Jev (Melvin Vivas on X · notes), Generating a Repo Promo Video with a Claude Skill on Sonnet 5.5 vs Opus 5.5 (Melvin Vivas on X · notes) and 15 more - Decision Index 0.2.1 · tool · github.com · free
The official benchmark scorer used to measure decision models across five evaluation areas.
More in LLM Fundamentals
- Run Local LLMs on the Computer You Already Have: A Beginner's Path
- Use Nvidia Nemotron 3.5 Lightning on OpenRouter for Cheap Worker Tasks
- xAI's Experimental TypeScript SDK: Grok Text, Voice, Image and Video in One SDK
- Use GPT-6.1 Sol by Default, Save Astra for Emergencies
- Use Sonnet 5.5 instead of Opus 5.5 for faster video-clipping tasks
- Guide: Building with Claude Sonnet 5.5