15 articles

#llm

All articles tagged with #llm.

Claude Fable 5 Is Back Online, and Free Until July 7

Anthropic's most capable model returned July 1 after a US export-control blackout. Here's what Fable 5 does, what it costs, and how to use the free week.

Jul 1, 20267 min

News

Claude Sonnet 5 vs Opus 4.8: When to Pay More

Sonnet 5 hits ~91% of Opus 4.8's agentic-coding score at 40% of the price. A routing rule for agents: default to Sonnet 5, and when Opus still earns it.

Jun 30, 20266 min

News

Prompt Injection: The #1 Security Risk for AI Apps

Prompt injection is the top vulnerability in LLM apps. See how the attack works, why AI agents make it worse, and how to actually defend your code.

Jun 28, 20267 min

AI & ML

Capstone: Build a Chat-With-Your-Notes AI App

Capstone project: build a 'chat with your notes' AI app in Python with RAG, retrieval, and citations end to end, then where to go next.

Jun 22, 202612 min

AI & ML

LLM Apps: Tokens, Cost, Latency and Safety

Tokens, cost, latency, and safety for LLM apps: count tokens, estimate cost, retry with backoff, and defend against prompt injection.

Jun 22, 202610 min

AI & ML

Build a Simple AI Agent in Python

Build a simple AI agent in Python: the think-act-observe loop, tool use, and memory, so the model can take steps, not just answer once.

Jun 21, 202610 min

AI & ML

RAG: Chat With Your Own Documents in Python

Build retrieval-augmented generation in Python: chunk, embed, retrieve, and ground an LLM's answers in your own documents with a working mini-RAG.

Jun 21, 202610 min

AI & ML

Tool Calling: Let the LLM Use Your Functions

Let an LLM call your Python functions with tool calling: define tools, run the call loop, and feed results back so the model can finish the job.

Jun 20, 20268 min

AI & ML

Control LLM Output: Temperature, Tokens, Streaming

Control LLM output in Python: temperature, top_p, max_tokens, stop sequences, and streaming responses token by token, with an interactive demo.

Jun 19, 20269 min

AI & ML

Get Structured JSON Output You Can Trust

Get structured JSON out of an LLM reliably: JSON mode, a Pydantic schema, validation, and retries, so your code can trust the model's output.

Jun 19, 20268 min

AI & ML

Prompts and the Message Format, Explained

How LLM prompts really work: the messages array, system/user/assistant roles, and keeping multi-turn conversation state in Python.

Jun 18, 20268 min

AI & ML

Prompt Engineering That Actually Works

Practical prompt engineering for developers: be specific, use few-shot examples, fix the format, and dodge the failure modes that waste tokens.

Jun 18, 202610 min

AI & ML

Make Your First LLM API Call in Python

Make your first LLM API call in Python using the OpenAI-compatible SDK. Set up a client, keep your key safe, and get a real model response.

Jun 17, 20267 min

AI & ML

What an LLM Actually Is (and What It Isn't)

What a large language model really is: next-token prediction, tokens, training vs inference, and what LLMs are good and bad at, with a live demo.

Jun 17, 202610 min

News

The 2026 LLM Price War: Near-Frontier for Cents

Cheap Chinese models now post near-frontier scores at a tenth of the price. What collapsing inference cost means for anyone building with LLMs.

Jun 16, 20269 min