FMOps

Foundation model operations in practice: RAG, fine-tuning, deployment, monitoring & vector databases. Turing Post's FMOps series for AI engineers.

AI 101

11 min read

May 6, 2026

AI 101: Agentic Vector Databases – What Is That?

How vector databases are evolving for AI agents: agentic RAG with Qdrant, memory layers with Weaviate Engram, and Pinecone Nexus knowledge engine explained.

Alyona Vert.

Concepts

AI 101: How Token Taxonomy Affects Your Bill

13 min read

Apr 22, 2026

AI 101: How Token Taxonomy Affects Your Bill

Input, output, reasoning, cached, vision — not all LLM tokens cost the same. A guide to token types and how each one shapes your AI bill.

Ksenia Se

FMOps

5 min read

Apr 3, 2024

Recap#2: How does FMOps Infrastructure Stack look like?

+ our best explanatory tokens about it, including a list of open-source tools, libraries, and companies

Ksenia Se

FMOps

3 min read

Mar 27, 2024

Recap#1 of FMOps: key concepts, techniques, and resources

Systematizing the knowledge about foundation models that are the backbone of generative AI

Ksenia Se, +1

FMOps

Token 1.24: Understanding Multimodal Models

8 min read

Mar 13, 2024

Token 1.24: Understanding Multimodal Models

Multimodal models explained: what they are, how fusion works, and key architectures from CLIP to Gemini. Examples, surveys & future directions.

Ksenia Se, +1

FMOps

Token 1.23: Mitigating Bias in Foundation Models/LLMs

6 min read

Mar 6, 2024

Token 1.23: Mitigating Bias in Foundation Models/LLMs

Your guide on how to identify bias, a few debiasing techniques, and collection of tools and libraries for detection and mitigation

Ksenia Se

FMOps

9 min read

Feb 28, 2024

Token 1.22: Data Privacy in LLM systems

How to protect data privacy in LLM systems: data leakage risks, anonymization, differential privacy, federated learning, and GDPR compliance.

Ksenia Se, +1

FMOps

Token 1.21: Vulnerabilities in LLMs and how to deal with them

7 min read

Feb 21, 2024

Token 1.21: Vulnerabilities in LLMs and how to deal with them

Explore the most common LLM vulnerabilities, from prompt injection to retrieval attacks, and learn how to defend AI systems effectively.

Bhuwan Bhatt

FMOps

Token 1.20: Explainable AI techniques and tools for LLMs

8 min read

Feb 14, 2024

Token 1.20: Explainable AI techniques and tools for LLMs

A guide to Explainable AI (XAI) for LLMs: techniques like surrogate models and attention visualization, plus tools such as SHAP, LIME, and Captum.

Bhuwan Bhatt

FMOps

Token 1.19: How to optimize LLM Inference

7 min read

Feb 7, 2024

Token 1.19: How to optimize LLM Inference

How to optimize LLM inference: TensorRT, GPU vs TPU, AWS accelerators, model serialization, and deployment best practices for large language models.

Ksenia Se, +1

FMOps

6 min read

Jan 31, 2024

Token 1.18: How to Monitor LLMs

A practical guide to monitoring LLMs: which open-source tools to use, the KPIs that matter, A/B testing, and adversarial attack risks.

Bhuwan Bhatt

FMOps

Token 1.17: LLM Deployment Best Practices for Production

9 min read

Jan 17, 2024

Token 1.17: LLM Deployment Best Practices for Production

Practical guide to deploying ML models and LLMs in production: model selection, embedding storage, infrastructure choices, and performance monitoring.

Bhuwan Bhatt

FMOps

Token 1.16:What Is RLHF? Reinforcement Learning from Human Feedback

8 min read

Jan 10, 2024

Token 1.16:What Is RLHF? Reinforcement Learning from Human Feedback

RLHF (Reinforcement Learning from Human Feedback) explained: 3-step pipeline with PPO, use cases, limitations, and how it enabled ChatGPT and InstructGPT.

Ksenia Se

FMOps

Token 1.15: What are AI Hallucinations: a Critical Challenge or an Opportunity?

9 min read

Jan 3, 2024

Token 1.15: What are AI Hallucinations: a Critical Challenge or an Opportunity?

Why LLMs hallucinate, the difference between faithfulness and factuality errors, how to detect them, and practical ways to reduce hallucinations.

Ksenia Se, +1

FMOps

8 min read

Dec 27, 2023

A Halfway Recap – Decoding FMOps: From Basics to Advanced RAG and CoT

Organizing emerging knowledge in real-time

Ksenia Se, +1

FMOps

Token 1.14: What is Synthetic Data and How to Work with it?

8 min read

Dec 20, 2023

Token 1.14: What is Synthetic Data and How to Work with it?

Synthetic data is artificially generated to mimic real datasets. Learn how it's created, when to use it for ML training, and how to evaluate its quality.

Bhuwan Bhatt

FMOps

Token 1.13: Where to Get Data for Data-Hungry Foundation Models

8 min read

Dec 13, 2023

Token 1.13: Where to Get Data for Data-Hungry Foundation Models

Explore how data is gathered to train FMs, learn a few data efficient training techniques and the ethics of data

Ksenia Se, +1

FMOps

6 min read

Dec 6, 2023

Token 1.12: What is Vector Database's Role in FMOps?

We explain what vector databases are and how they work, explore alternative solutions and provide expert insight on security

Ksenia Se

FMOps

Token 1.11: What is Low-Rank Adaptation (LoRA)?

6 min read

Nov 29, 2023

Token 1.11: What is Low-Rank Adaptation (LoRA)?

LoRA fine-tunes LLMs without retraining the full model. How low-rank matrices work, why LoRA cuts memory costs, and when to use it vs full fine-tuning.

Valeriia Kuka

FMOps

Token 1.10: Large vs Small in AI: The Language Model Size Dilemma

9 min read

Nov 22, 2023

Token 1.10: Large vs Small in AI: The Language Model Size Dilemma

LLM vs SLM: inference costs, compression techniques, and when to use small or large language models.

Valeriia Kuka

FMOps

Token 1.9: Open- vs Closed-Source AI Models: Which is the Better Choice for Your Business?

9 min read

Nov 15, 2023

Token 1.9: Open- vs Closed-Source AI Models: Which is the Better Choice for Your Business?

A Deep Dive into the Pros and Cons of Each Approach with a Few Useful Tips

Ksenia Se, +1

FMOps

Token 1.8: Silicon Valley of AI Chips and Semiconductors

10 min read

Nov 8, 2023

Token 1.8: Silicon Valley of AI Chips and Semiconductors

Understanding the Chips that Drive Today's AI Breakthroughs

Ksenia Se

FMOps

Token 1.7: What Are Chain-of-Verification, Chain of Density, and Self-Refine?

7 min read

Nov 1, 2023

Token 1.7: What Are Chain-of-Verification, Chain of Density, and Self-Refine?

Your Expert Guide to Seminal Concepts in AI Chaining

Ksenia Se, +1

FMOps

Token 1.6: Transformer and Diffusion-Based Foundation Models

8 min read

Oct 25, 2023

Token 1.6: Transformer and Diffusion-Based Foundation Models

An overview of Transformer-based models (BERT, GPT) and diffusion-based models (Stable Diffusion, DALL-E, Imagen, Midjourney): how each architecture works.

Ksenia Se, +1

FMOps

Token 1.5: From Chain-of-Thoughts to Skeleton-of-Thoughts, and everything in between

9 min read

Oct 18, 2023

Token 1.5: From Chain-of-Thoughts to Skeleton-of-Thoughts, and everything in between

How to distinguish all the СoT-inspired concepts and use them for your projects

Ksenia Se, +1