BestHub
Sign in
AI Engineer Programming
Author

AI Engineer Programming

In the AI era, defining problems is often more important than solving them; here we explore AI's contradictions, boundaries, and possibilities.

145
Articles
0
Likes
1.1k
Views
0
Comments
Recent Articles

Latest from AI Engineer Programming

100 recent articles max
AI Engineer Programming
AI Engineer Programming
Jul 23, 2026 · R&D Management

When Companies Mandate AI-Only Coding, Budgets Override Real Productivity

A junior engineer recounts how his Norwegian tech firm first forced developers to code exclusively with AI, then imposed strict token budgets and bonuses, leading senior staff to abandon AI tools, revealing that financial incentives, not actual productivity gains, dominate corporate AI adoption decisions.

AI CodingSoftware Engineeringindustry trends
0 likes · 7 min read
When Companies Mandate AI-Only Coding, Budgets Override Real Productivity
AI Engineer Programming
AI Engineer Programming
Jul 22, 2026 · Artificial Intelligence

Is Prompt Engineering Dead? A Deep Dive into Harness, Context Assembly, and Token Generation

The article examines why traditional prompt engineering is no longer sufficient in production AI systems, detailing how harness layers, context reassembly, tool orchestration, token generation methods, training objectives, and architecture choices transform a simple prompt into a complex, multi‑stage workflow that demands robust, system‑level design.

HarnessLLMMulti-Token Prediction
0 likes · 16 min read
Is Prompt Engineering Dead? A Deep Dive into Harness, Context Assembly, and Token Generation
AI Engineer Programming
AI Engineer Programming
Jul 21, 2026 · Artificial Intelligence

Understanding EOS, stop_token_ids, and stop_sequences in vLLM

This article dissects how vLLM handles generation termination by comparing token‑level EOS, token‑level stop_token_ids, and string‑level stop/stop_sequences, detailing where each check occurs, how they affect the Scheduler and Detokenizer, and how finish_reason and stop_reason are derived for the API response.

BackendEOSLLM
0 likes · 13 min read
Understanding EOS, stop_token_ids, and stop_sequences in vLLM
AI Engineer Programming
AI Engineer Programming
Jul 19, 2026 · Artificial Intelligence

Why Chat Templates Matter for LLMs: A Deep Dive into Jinja2‑Based Prompt Formatting

Large language models generate text autoregressively from flat token streams, but real‑world conversations require structured roles, system prompts, and multi‑turn history, so Hugging Face’s Jinja2‑driven chat templates serialize these elements, handle BOS/EOT tokens, enforce role alternation, and provide debugging tricks across Meta‑Llama‑3.1, Qwen2.5, and Mistral models.

ChatTemplateJinja2LLM
0 likes · 16 min read
Why Chat Templates Matter for LLMs: A Deep Dive into Jinja2‑Based Prompt Formatting
AI Engineer Programming
AI Engineer Programming
Jul 18, 2026 · Artificial Intelligence

13 Agentic AI Trends to Watch in 2026

The article analyzes thirteen emerging Agentic AI trends for 2026—including CLI agents, the resurgence of MCP, multi‑agent orchestration, agentic commerce, AI governance, personal assistants, context engineering, vertical agents, small language models, recursive LMs, real‑time web access, browser agents, and verifiability—backed by data, case studies, and industry reports.

AI GovernanceAgentic AICLI agents
0 likes · 29 min read
13 Agentic AI Trends to Watch in 2026
AI Engineer Programming
AI Engineer Programming
Jul 17, 2026 · Backend Development

Choosing the Right Streaming Protocol for AI: Comparing Five Options (Part 2)

This article analyzes five streaming protocols for AI—including gRPC Stream, Streamable HTTP (MCP), SSE, WebSocket, and HTTP Chunked—detailing their mechanisms, code examples, pros and cons, and provides a decision matrix to help engineers select the most suitable protocol based on connection model, data format, infrastructure compatibility, and development complexity.

AI streamingMCPProtocol Selection
0 likes · 14 min read
Choosing the Right Streaming Protocol for AI: Comparing Five Options (Part 2)
AI Engineer Programming
AI Engineer Programming
Jul 15, 2026 · Backend Development

Choosing the Right Protocol for AI Streaming: SSE, Chunked, or WebSocket (Part 1)

This article analyzes three HTTP‑based streaming approaches—Server‑Sent Events (SSE), HTTP Chunked Transfer Encoding, and WebSocket—detailing their underlying mechanisms, implementation steps, pros and cons, and ideal use cases to help developers select the most suitable protocol for AI‑driven real‑time output.

AI streamingHTTP ChunkedProtocol Selection
0 likes · 17 min read
Choosing the Right Protocol for AI Streaming: SSE, Chunked, or WebSocket (Part 1)
AI Engineer Programming
AI Engineer Programming
Jul 14, 2026 · Backend Development

How vLLM Generates Tokens: A Deep Dive into the Source Code

This article walks through vLLM’s token‑generation pipeline by dissecting its source files, process roles, ZMQ communication, scheduling, and deployment considerations, revealing how prompts become streamed token IDs and highlighting the key factors that limit concurrency and performance.

DeploymentGPU memoryLLM Inference
0 likes · 17 min read
How vLLM Generates Tokens: A Deep Dive into the Source Code