Thousand Miles AI

Thousand Miles is a group of engineers dedicated to empowering the masses to understand AI and software engineering. We believe that education is the foundational stone for building a knowledgeable so

Bengaluru, India Joined on Feb 27, 2026 https://thousandmiles.ai

Thousand Miles AI

May 22

Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench

#ai #llm #opensource #agents

4 min read

Thousand Miles AI

May 22

WebMCP in Chrome 149: web pages get a tool API for AI agents

#ai #agents #webdev #explained

4 min read

Thousand Miles AI

May 22

ZAYA1-8B: a 760M-active MoE trained on AMD MI300x

#ai #llm #moe #openweights

5 min read

Thousand Miles AI

May 22

Cola DLM — Text Generation That Plans Before It Writes

#ai #llm #diffusion #explained

4 min read

Thousand Miles AI

May 22

Your "Claude Opus" API Might Not Be Claude Opus

#ai #llm #security #explained

4 min read

Thousand Miles AI

May 21

What "Subquadratic Attention" Actually Means

#ai #llm #explained #transformers

4 min read

Thousand Miles AI

May 21

Three RAG failures that look like model problems but aren't

#ai #llm #tutorial #rag

6 min read

Thousand Miles AI

May 19

The silent sequential skip: a failure class every AI pipeline should name

#discuss #ai #programming #reliability

5 min read

Thousand Miles AI

May 19

The graduation AI that skipped names — and what it taught us about silent failure

#watercooler #ai #programming #agents

5 min read

Thousand Miles AI

May 19

The boring engineering you skipped is the headline you'll wear

#discuss #ai #programming #devops

5 min read

Thousand Miles AI

May 19

Sharing your prompts is the new telling people your dreams

#watercooler #ai #llm #discuss

3 min read

Thousand Miles AI

May 19

Your model speed benchmark is measuring the wrong thing

#discuss #ai #llm #benchmarking

3 min read

Thousand Miles AI

May 19

Your AI speed benchmark is measuring the one workload you don't run

#discuss #ai #llm #inference

3 min read

Thousand Miles AI

May 18

Context engineering is an architecture strategy, not a model swap

#discuss #ai #agents #programming

6 min read

Thousand Miles AI

May 17

The cracked mirror: why AI hallucination is structural, not a bug

#discuss #ai #llm #rag

6 min read

Thousand Miles AI

May 16

Hallucination is not a bug — it is the shape of the machine

#discuss #ai #llm #programming

4 min read

Thousand Miles AI

Mar 6

How LLMs Actually Generate Text — Temperature, Top-K, Top-P, and the Dice Rolls You Never See

#learning #ai #softwareengineering

7 min read

Thousand Miles AI

Mar 6

The LLM Interview Cheat Sheet — 10 Questions That Actually Come Up

#learning #ai

11 min read

Thousand Miles AI

Mar 6

How AI Agents Actually Execute Multi-Step Tasks — The Orchestration Nobody Talks About

#learning #ai #softwareengineering

7 min read

Thousand Miles AI

Mar 6

How to Evaluate LLM Outputs — Beyond 'Looks Good to Me'

#learning #ai

8 min read

Thousand Miles AI

Mar 6

How DeepSeek R1 Shocked the World (And Why It Matters to You)

#ai #opensource #technology

9 min read

Thousand Miles AI

Mar 6

Context Engineering Is the New Prompt Engineering

#ai #productivity #softwareengineering

7 min read

Thousand Miles AI

Mar 6

Running LLMs on Your Laptop Without a $10K GPU

#learning #ai #softwareengineering #llms

7 min read

Thousand Miles AI

Mar 6

What Are Reasoning Models and Why Do They Think Before Answering?

#learning #ai

7 min read

Thousand Miles AI

Mar 6

The 'Lost in the Middle' Problem — Why LLMs Ignore the Middle of Your Context Window

#learning #ai

7 min read

Thousand Miles AI

Mar 6

LoRA and QLoRA Explained — Fine-Tune LLMs Without Selling Your Kidney for GPUs

#learning #ai

8 min read

Thousand Miles AI

Mar 6

Chunking Strategies That Actually Work — Why Your RAG App Retrieves Garbage

#learning #ai #softwareengineering

7 min read

Thousand Miles AI

Mar 6

Build Your First MCP Server in Python — A Weekend Project That Actually Impresses

#learning #ai #softwareengineering

7 min read

Thousand Miles AI

Mar 6

AI-Generated Code Fails in Production (and Why Your Manager Won't Notice)

#ai #softwareengineering #qualityassurance

6 min read

DEV Community

Thousand Miles AI

Badges

Writing Debut

Organizations

Thousand Miles AI

Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench

WebMCP in Chrome 149: web pages get a tool API for AI agents

ZAYA1-8B: a 760M-active MoE trained on AMD MI300x

Cola DLM — Text Generation That Plans Before It Writes

Your "Claude Opus" API Might Not Be Claude Opus

What "Subquadratic Attention" Actually Means

Three RAG failures that look like model problems but aren't

The silent sequential skip: a failure class every AI pipeline should name

The graduation AI that skipped names — and what it taught us about silent failure

The boring engineering you skipped is the headline you'll wear

Sharing your prompts is the new telling people your dreams

Your model speed benchmark is measuring the wrong thing

Your AI speed benchmark is measuring the one workload you don't run

Context engineering is an architecture strategy, not a model swap

The cracked mirror: why AI hallucination is structural, not a bug

Hallucination is not a bug — it is the shape of the machine

How LLMs Actually Generate Text — Temperature, Top-K, Top-P, and the Dice Rolls You Never See

The LLM Interview Cheat Sheet — 10 Questions That Actually Come Up

How AI Agents Actually Execute Multi-Step Tasks — The Orchestration Nobody Talks About

How to Evaluate LLM Outputs — Beyond 'Looks Good to Me'

How DeepSeek R1 Shocked the World (And Why It Matters to You)

Context Engineering Is the New Prompt Engineering

Running LLMs on Your Laptop Without a $10K GPU

What Are Reasoning Models and Why Do They Think Before Answering?

The 'Lost in the Middle' Problem — Why LLMs Ignore the Middle of Your Context Window

LoRA and QLoRA Explained — Fine-Tune LLMs Without Selling Your Kidney for GPUs

Chunking Strategies That Actually Work — Why Your RAG App Retrieves Garbage

Build Your First MCP Server in Python — A Weekend Project That Actually Impresses

AI-Generated Code Fails in Production (and Why Your Manager Won't Notice)