Forem

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Step-by-Step: Manual vLLM Setup on Google Cloud L4 (Debian)

Step-by-Step: Manual vLLM Setup on Google Cloud L4 (Debian)

Comments
2 min read
Structured prompts: how YAML cut my LLM costs by 30%

Structured prompts: how YAML cut my LLM costs by 30%

Comments
3 min read
🧩 Runtime Snapshots #3 — QA That Speaks JSON
Cover image for 🧩 Runtime Snapshots #3 — QA That Speaks JSON

🧩 Runtime Snapshots #3 — QA That Speaks JSON

4
Comments
1 min read
Gemini 2.5 Flash-Lite: Speed > Scale — 887 TPS, 50% Less Verbosity, Real-World Wins

Gemini 2.5 Flash-Lite: Speed > Scale — 887 TPS, 50% Less Verbosity, Real-World Wins

Comments
1 min read
About context and LLM
Cover image for About context and LLM

About context and LLM

2
Comments
7 min read
Building Effective Prompt Engineering Strategies for AI Agents

Building Effective Prompt Engineering Strategies for AI Agents

Comments 1
7 min read
How to Build Developer Trust in AI‑Powered Code Generation Through Data‑Driven Feedback and Evaluation

How to Build Developer Trust in AI‑Powered Code Generation Through Data‑Driven Feedback and Evaluation

1
Comments 1
8 min read
How to Improve Cross-Lingual Retrieval Accuracy in Bilingual RAG Chatbots

How to Improve Cross-Lingual Retrieval Accuracy in Bilingual RAG Chatbots

1
Comments 1
9 min read
Granite 4: IBM introduces a line of small but fast LLMs

Granite 4: IBM introduces a line of small but fast LLMs

Comments
2 min read
OpenAI's SORA 2 Release Pattern: What It Means for AI Video
Cover image for OpenAI's SORA 2 Release Pattern: What It Means for AI Video

OpenAI's SORA 2 Release Pattern: What It Means for AI Video

Comments
9 min read
The RAG Debugging Playbook: A Step-by-Step Guide to Trace-Level Failures and Fixes

The RAG Debugging Playbook: A Step-by-Step Guide to Trace-Level Failures and Fixes

Comments
10 min read
Synthetic Data for RAG: Safe Generation, Deduplication, and Drift-Aware Curation in 2025

Synthetic Data for RAG: Safe Generation, Deduplication, and Drift-Aware Curation in 2025

2
Comments
10 min read
🚀 TOON (Token-Oriented Object Notation) — The Smarter, Lighter JSON for LLMs
Cover image for 🚀 TOON (Token-Oriented Object Notation) — The Smarter, Lighter JSON for LLMs

🚀 TOON (Token-Oriented Object Notation) — The Smarter, Lighter JSON for LLMs

49
Comments 18
3 min read
Why We Need AI Observability

Why We Need AI Observability

1
Comments 1
9 min read
AI Browsers and Prompt Injection: The New Cybersecurity Frontier
Cover image for AI Browsers and Prompt Injection: The New Cybersecurity Frontier

AI Browsers and Prompt Injection: The New Cybersecurity Frontier

3
Comments 5
6 min read
Spatial Secrets: Unleashing Language Models with Unexpected Masking by Arvind Sundararajan

Spatial Secrets: Unleashing Language Models with Unexpected Masking by Arvind Sundararajan

Comments
2 min read
Post‑Evaluation Action Plan for AI Agents

Post‑Evaluation Action Plan for AI Agents

Comments
5 min read
AI study assistant

AI study assistant

1
Comments
1 min read
Tool Calling dando mãos e olhos aos modelos de linguagem (LLMs)

Tool Calling dando mãos e olhos aos modelos de linguagem (LLMs)

Comments
12 min read
Harmonic RSI — Measuring Logical Resonance and Stability in AI Reasoning

Harmonic RSI — Measuring Logical Resonance and Stability in AI Reasoning

1
Comments
2 min read
App power by LLM and Tools in Elixir

App power by LLM and Tools in Elixir

Comments
2 min read
Tired of AI Hallucinations? I Built a RAG App to Keep My Research Grounded.

Tired of AI Hallucinations? I Built a RAG App to Keep My Research Grounded.

5
Comments 1
4 min read
From Parrot to Partner - How Reinforcement Learning Taught LLMs to Talk Like Humans

From Parrot to Partner - How Reinforcement Learning Taught LLMs to Talk Like Humans

3
Comments
13 min read
# Comprehensive Monitoring & Observability #llmszoomcamp

# Comprehensive Monitoring & Observability #llmszoomcamp

Comments
8 min read
Collateral Crossroads: Quantum-AI's Revolution in Risk Mitigation

Collateral Crossroads: Quantum-AI's Revolution in Risk Mitigation

Comments
2 min read
loading...