All creators
AI WITH Rithesh

AI WITH Rithesh

AI software and models with a focus on practical testing and benchmark performance.

YouTube
Trust
7.7
Last scored Mar 18, 2026
Award
Worth Prioritizing
Chart
#30
AI & Software Tools
Subscribers
51K
YouTube
Age
5y 9m
Channel age

Nutrition Label

Deep dives into new AI software and models, testing them with real-world prompts and benchmarks.

Strengths

  • +Practical testing
  • +Clear demonstrations
  • +Technical insight

Notes

  • !Check the description for potential disclosures or affiliate links.
  • !The creator provides hands-on testing of new AI tools.

Why this score

Experience Authenticity · 01:54
“I've chosen this 3.5 model over here and I said like I need to get a car wash done...”

Demonstrates real-time interaction with the model.

Open receipt

Trust Breakdown

Evidence Quality
7.8
Firsthand Access
8.0
Analysis Quality
6.2
Depth & Nuance
7.3
Disclosure Clarity
7.0
Framing Integrity
10.0

Review Lens: Hands-on evidence carries more weight.

Medium confidence. Based on 5 long-form videos.

These six Trust Core outputs drive the public creator rating. Communication affects discovery ranking separately. Methodology →

Recent Videos

Microsoft's MAI Strategy Explained: How Small Models Beat Frontier Prices (Copilot + Excel)
Pending

Microsoft's MAI Strategy Explained: How Small Models Beat Frontier Prices (Copilot + Excel)

Jul 24, 2026 • 18 views
How AI Cracked an "Unsolvable" 87-Year Math Puzzle in Hours
Pending

How AI Cracked an "Unsolvable" 87-Year Math Puzzle in Hours

Jul 24, 2026 • 43 views
How AI Agents Actually Work: ReAct, Tools & Reflexion
Pending

How AI Agents Actually Work: ReAct, Tools & Reflexion

Jul 23, 2026 • 41 views
Loop Engineering Explained: The New Core Skill of Agentic AI
Pending

Loop Engineering Explained: The New Core Skill of Agentic AI

Jul 23, 2026 • 44 views
Cut LLM Cost & Latency: KV Cache, Batching, Quantization, vLLM
Pending

Cut LLM Cost & Latency: KV Cache, Batching, Quantization, vLLM

Jul 23, 2026 • 27 views
LLM Guardrails: Stop Injection, Leaks & Hallucination (NeMo Guardrails)
Pending

LLM Guardrails: Stop Injection, Leaks & Hallucination (NeMo Guardrails)

Jul 22, 2026 • 37 views
Production RAG (RAGOps): Hybrid Search, Rerankers & HNSW
Pending

Production RAG (RAGOps): Hybrid Search, Rerankers & HNSW

Jul 22, 2026 • 48 views
LLM Observability: Traces, Spans & OpenTelemetry for AI Apps
Pending

LLM Observability: Traces, Spans & OpenTelemetry for AI Apps

Jul 21, 2026 • 78 views
Kimi K3 Why Is It So Powerful — The Architecture Deep Dive! Delta Attention, Attention Residuals
Pending

Kimi K3 Why Is It So Powerful — The Architecture Deep Dive! Delta Attention, Attention Residuals

Jul 21, 2026 • 230 views
How to Evaluate LLM Apps: LLM-as-a-Judge & RAGAS (Without the Bias)
Pending

How to Evaluate LLM Apps: LLM-as-a-Judge & RAGAS (Without the Bias)

Jul 21, 2026 • 66 views
Prompt Management as Code: Versioning, Injection & DSPy
Pending

Prompt Management as Code: Versioning, Injection & DSPy

Jul 20, 2026 • 41 views
Qwen 3.8 First Impressions: Massive Upgrade or Overhyped?
Pending

Qwen 3.8 First Impressions: Massive Upgrade or Overhyped?

Jul 20, 2026 • 698 views
LLMOps → Agentic AIOps: Start Here (Playlist Intro)
Pending

LLMOps → Agentic AIOps: Start Here (Playlist Intro)

Jul 20, 2026 • 33 views
RLHF vs DPO vs GRPO: Which Method, and When RL for LLMs
Pending

RLHF vs DPO vs GRPO: Which Method, and When RL for LLMs

Jul 19, 2026 • 50 views
Qwen 3.8 2.4T Model Released Open Weights Coming Soon Second Only to Fable 5
Pending

Qwen 3.8 2.4T Model Released Open Weights Coming Soon Second Only to Fable 5

Jul 19, 2026 • 195 views

Shareable card

A compact ReReview card and short URL for sharing this trust score.

AI WITH Rithesh
ReReview Trust Score
7.7
Worth Prioritizing
rereview.co/c/ai-with-rithesh
Canonical: rereview.co/creators/ai-with-rithesh
Categories
AI AssistantsAutomation & AgentsCoding ToolsCreative ToolsData & AnalyticsResearch ToolsVideo Generation
Formats
ReviewsDeep Dives