Models & Tool Choice

11 min read

Article

Self-hosted vs hosted inference: vLLM, TGI, and the break-even math

At what scale does self-hosting beat API calls? The actual math, the operational realities, and the patterns that distinguish teams who should self-host from teams who should keep paying for managed inference.

Use the article as decision context for adoption, risk, governance, or investment choices.

Advanced

12 min read

Article

Cost-optimizing inference: prompt caching, routing, and output control

LLM inference costs are 60-90% reducible with the right techniques. Prompt caching, model routing, output control, batching, and a few less-known patterns. The numbers, the patterns, and the production discipline that distinguishes well-run inference from a runaway bill.

Use the article as decision context for adoption, risk, governance, or investment choices.

Advanced

13 min read

Article

Fine-tuning in 2026: when LoRA beats RAG, and how to do it without a cluster

LoRA fine-tuning has become accessible — you can run real fine-tunes on a laptop or rent a GPU for an hour. The patterns that work, the cases where fine-tuning beats RAG, and a practical end-to-end workflow from data prep to deployment.

Evaluate the implementation pattern, failure modes, and guardrails before building.

Advanced

12 min read

Article

Choosing between prompting, RAG, and fine-tuning (and when to combine)

Prompting, RAG, and fine-tuning are the three big levers for adapting LLMs to your problem. Each is right for some problems and wrong for others. A framework for choosing, the realistic costs of each, and the production patterns where combining them shines.

Use the article as decision context for adoption, risk, governance, or investment choices.

Advanced

13 min read

Article

The 2026 LLM stack: models, inference, tooling, and trade-offs

A working architect's view of the 2026 LLM stack — the model tiers, inference providers, orchestration layers, evaluation tooling, and the trade-offs that actually matter when shipping production AI. Everything you wish someone had laid out before you started.

Use the article as decision context for adoption, risk, governance, or investment choices.

Advanced

10 min read

Article

Local AI on your Mac: Ollama, LM Studio, and what 7B models can really do

Running AI locally has matured. With Ollama or LM Studio and a modern Mac, you can run capable models offline, free, and private. What works, what doesn't, and the use cases that actually benefit.

Evaluate the implementation pattern, failure modes, and guardrails before building.

Intermediate

10 min read

Article

Prompt engineering for reasoning models (o3, R1, Claude extended thinking)

Reasoning models are not fast models with extra steps. They reward different prompting, ignore some conventional patterns, and have their own pitfalls. A practical guide to working with them well.

Evaluate the implementation pattern, failure modes, and guardrails before building.

Intermediate

10 min read

Article

Chain-of-thought, self-critique, tree-of-thoughts — when to use each

Three reasoning techniques that genuinely improve AI output on hard problems — and the cost-benefit math of using them. With concrete prompts, side-by-side comparisons, and the gotchas modern reasoning models introduce.

Evaluate the implementation pattern, failure modes, and guardrails before building.

Intermediate

6 min read

Article

Free vs Paid ChatGPT: what you actually get for ~€20/month

A jargon-free comparison of free ChatGPT, ChatGPT Plus, and ChatGPT Pro — what changes when you upgrade and how to tell if you actually need to.

Understand the idea well enough to try it safely in a low-risk setting.

New to AI

32 minutes

Video

Fast LLM Serving with vLLM and PagedAttention

Anyscale. Walks through why naive LLM serving wastes 60–80% of GPU memory, how PagedAttention borrows OS-style paging to fix that, and why continuous batching produces the 24× throughput numbers the article uses in its math. After this, the article's "you'll be lucky to hit 50% utilisation" line stops feeling abstract.

Advanced

56 minutes

Video

Build Hour: Prompt Caching

OpenAI. OpenAI's own Build Hour on prompt caching — the 1024-token threshold, the prefix-stability requirement, audio caching at 99% discount for realtime, time-to-first-token impacts at long inputs. Useful when you are sizing the engineering effort to actually hit the cache reliably on your production prompts.

Advanced

19 minutes

Video

Is This the End of RAG? Anthropic's NEW Prompt Caching

Prompt Engineering. Walks through Anthropic's prompt caching against Gemini's context caching with concrete latency-and-cost reductions per use case (long-document chat, few-shot, multi-turn). The breakdown of cache-write surcharge vs. cache-read discount is exactly what the article assumes when it talks about when caching pays off.

Advanced

59 minutes

Video

Developing an LLM: Building, Training, Finetuning

Sebastian Raschka. Sebastian Raschka's slower walkthrough of where fine-tuning sits in the broader LLM training pipeline — instruction tuning, classification fine-tuning, parameter-efficient methods, and the trade-offs the article calls out before recommending LoRA. Good calibration before you start, especially if your team is debating whether fine-tuning is even the right step.

Advanced

157 minutes

Video

Fine Tuning LLM Models – Generative AI Course

freeCodeCamp.org. Long, theory-then-code course covering quantisation, LoRA, QLoRA, and full PEFT on Llama 2 and Gemma — on hardware most developers actually have. It is the closest thing to a "shadow somebody who has done this" experience on YouTube and lines up with the article's "you don't need a cluster" claim with concrete VRAM budgets.

Advanced

9 minutes

Video

RAG vs. Fine Tuning

IBM Technology. Tighter focus on the two techniques teams most often confuse. Goes deeper on data freshness, source attribution, and the inference-time speed argument for fine-tuning. Worth watching if you are specifically trying to argue against an unnecessary fine-tune project.

Advanced

13 minutes

Video

RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models

IBM Technology. A clear whiteboard pass through all three techniques with their respective costs — retrieval latency, training compute and catastrophic forgetting, the limits of prompt-only solutions — and the combinations that actually make sense in production. The closing example of a legal AI system using all three is almost exactly the article's "when to combine" argument.

Advanced

40 minutes

Video

Andrej Karpathy: Software Is Changing (Again)

Y Combinator. Karpathy's AI Startup School keynote frames LLMs as a new kind of computer — utility, fab, and OS rolled together — and argues for "partial autonomy" products with a human-controlled leash. It is the cleanest articulation of the stack-level mental model the article assumes: that you are picking inference vendors and tooling for a programmable substrate, not a chatbot.

Advanced

211 minutes

Video

Deep Dive into LLMs like ChatGPT

Andrej Karpathy. This is the clearest end-to-end explanation on YouTube of what an LLM actually is — pretraining, tokenization, SFT, RLHF, reasoning RL, tool use, hallucinations — at the level of detail an engineer needs to reason about model trade-offs. Watch it once and the "GPT-class vs. open-weights vs. reasoning model" decisions in the article stop feeling like brand choices and start feeling like training-recipe choices.

Advanced

9 minutes

Video

RouteLLM achieves 90% GPT4o Quality AND 80% CHEAPER

Matthew Berman. Walks through the LMSYS RouteLLM paper and code: a small classifier sits in front of a strong/weak model pair and decides which one to call, hitting roughly 95% of the strong model's quality at a fraction of the cost. The view count is under the usual 100k bar, but for the specific "show me real model routing, not just model comparisons" niche this is the cleanest explanation on YouTube and lines up directly with the article's quality/cost tradeoff section.

Intermediate

19 minutes

Video

Every AI Model Explained

Tina Huang. A clean tour of the current model landscape grouped by tier — flagships, lite models, mid-tier, specialized — with concrete picks for what each tier is actually good for. This is the "know your options before you route" half of the article, and Huang frames cost-vs-capability the same way the article does without leaning on benchmark hype.

Intermediate

17 minutes

Video

The New, Smartest AI: Claude 3 – Tested vs Gemini 1.5 + GPT-4

AI Explained. Older than the article (March 2024), but the methodology is what's useful: a single careful reviewer running the same hard tasks — OCR, theory of mind, instruction following, math — through three frontier models side by side and showing exactly where each one cracks. The model names are dated, the framework for comparing models is not.

Beginner

131 minutes

Video

How I use LLMs

Andrej Karpathy. Karpathy spends explicit chapters on "Be aware of the model you're using, pricing tiers" and "Thinking models and when to use them," then keeps switching between ChatGPT, Claude, Gemini, Grok, and Perplexity throughout the rest of the walkthrough. It is the closest thing to watching the article's cheat sheet applied live by someone with strong opinions about when each tier earns its keep.

Beginner

19 minutes

Video

Every AI Model Explained

Tina Huang. A calm 19-minute map of the major model families — OpenAI's GPT line, Anthropic's Claude, Google's Gemini, plus the open-source players — and which tier inside each family is worth your time. After the article tells you "pick one and stick with it for a month," this video tells you what the dropdown menu inside that one is actually offering. Honestly opinionated without being a hot take.

New to AI

15 minutes

Video

Is ChatGPT Plus Worth it? Here's My Updated Review for 2025

Ryan Doser. Ryan walks through every feature actually gated behind the $20 tier — usage caps, advanced voice mode, image and Sora limits, custom GPTs, the o1 family — and contrasts it with current free alternatives like Claude, Gemini, and Perplexity. The view count is on the lower side because the topic is narrow, but this is the cleanest current side-by-side that doesn't dissolve into hype, which is why we picked it over the louder "Plus changed my life" videos.

New to AI

Start here

ChatGPT, Claude, Gemini, Copilot — which should a beginner pick?

Picking the right model for the job: a 2026 decision cheat sheet

Multi-model orchestration: routing by cost, latency, and quality

More in this topic

Self-hosted vs hosted inference: vLLM, TGI, and the break-even math

Cost-optimizing inference: prompt caching, routing, and output control

Fine-tuning in 2026: when LoRA beats RAG, and how to do it without a cluster

Choosing between prompting, RAG, and fine-tuning (and when to combine)

The 2026 LLM stack: models, inference, tooling, and trade-offs

Local AI on your Mac: Ollama, LM Studio, and what 7B models can really do

Prompt engineering for reasoning models (o3, R1, Claude extended thinking)

Chain-of-thought, self-critique, tree-of-thoughts — when to use each

Free vs Paid ChatGPT: what you actually get for ~€20/month

Fast LLM Serving with vLLM and PagedAttention

Build Hour: Prompt Caching

Is This the End of RAG? Anthropic's NEW Prompt Caching

Developing an LLM: Building, Training, Finetuning

Fine Tuning LLM Models – Generative AI Course

RAG vs. Fine Tuning

RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models

Andrej Karpathy: Software Is Changing (Again)

Deep Dive into LLMs like ChatGPT

RouteLLM achieves 90% GPT4o Quality AND 80% CHEAPER

Every AI Model Explained

The New, Smartest AI: Claude 3 – Tested vs Gemini 1.5 + GPT-4

How I use LLMs

Every AI Model Explained

Is ChatGPT Plus Worth it? Here's My Updated Review for 2025