Sandi Besen – Medium

Pinned

Sandi Besen
in
Towards Data Science

The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A…

We set out to uncover the key design elements for AI Agents to effectively execute complex goals. This article summarizes our findings.

7 min readApr 23, 2024

--

5

The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A…

--

5

Pinned

Sandi Besen
in
AI Mind

LLM Embeddings — Explained Simply

Embeddings are the fundamental reasons why large language models such as OpenAi’s GPT-4 and Anthropic’s Claude are able to contextualize…

4 min readJul 25, 2023

--

3

LLM Embeddings — Explained Simply

--

3

Sandi Besen
in
Towards Data Science

The Limitations and Advantages of Retrieval Augmented Generation (RAG)

Exploring situations in which Retieval Augemented Generation (RAG) excels and those in which it falls short

4 min readApr 15, 2024

--

The Limitations and Advantages of Retrieval Augmented Generation (RAG)

--

Sandi Besen
in
Towards Data Science

The Death of the Static AI Benchmark

Benchmarks are often hailed as a hallmark of success but recent research studies and industry grumblings are casting doubt about their…

3 min readMar 21, 2024

--

1

The Death of the Static AI Benchmark

--

1

Sandi Besen
in
AI Mind

AI : From Helper to Human Validator

Will Language Models Transition from Helper to Mandatory Validator?Read More About its Potential Benefits and Risks in This Thought Piece.

4 min readMar 12, 2024

--

1

AI : From Helper to Human Validator

--

1

Sandi Besen
in
AI Mind

There’s a New Winner in Town — Anthropic’s Claude 3

Anthropic’s Claude3 models now reign against other top performing models like GPT and Gemini

3 min readMar 5, 2024

--

There’s a New Winner in Town — Anthropic’s Claude 3

--

Sandi Besen
in
AI Mind

Advanced Language Model Reasoning: Pre-Training , Fine-Tuning, and Inference Time Techniques

Advanced strategies to bolster a language model reasoning capabilities through pre-training, fine-tuning, and prompting/inference…

5 min readMar 5, 2024

--

Advanced Language Model Reasoning: Pre-Training , Fine-Tuning, and Inference Time Techniques

--

Sandi Besen

A Breakthrough in Language Model Reasoning with Orca2

MSFT makes leaps in the field of Artificial Intelligence Reasoning with their Small Language Model (SLM) Orca2.

4 min readJan 30, 2024

--

2

A Breakthrough in Language Model Reasoning with Orca2

--

2

Sandi Besen
in
Neudesic Innovation

AI Agents — The Age of The AI Employee

Our relationship with AI is about to change. AI Agents are enabling the first iteration of AI Employees that can collaborate as a team.

4 min readJan 24, 2024

--

2

AI Agents — The Age of The AI Employee

--

2

Sandi Besen
in
AI Mind

Rise of the SLM (Small Language Model)

SLMs Take Center Stage: Efficiency, Flexibility, Energy consumption, Data Security, and Task Specific Customization

3 min readDec 5, 2023

--

1

Rise of the SLM (Small Language Model)

--

1

Sandi Besen

Sandi Besen

Learn along side me as I publish technical but digestible content for technical SMEs and novices alike. My opinons may not represent those of my employer.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams