All
Articles 171,282Blog Posts 162,912Tech Tutorials 45,677Research Papers 33,276News 21,690
⚡ AI Lessons
![[Day 20] Local AI vs cloud AI: one cat photo, 10 video models](https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F9fm8ojdlgzyxr357flne.png)
Dev.to · PEPPERCORN
🧠 Large Language Models
⚡ AI Lesson
3w ago
[Day 20] Local AI vs cloud AI: one cat photo, 10 video models
Day 20 of my 100-experiment local LLM challenge. Same photo, same prompt, 10 video models — half on a local DGX Spark, half in the cloud. Easy prompt: no differ
![[Day 17] I analyzed 33,469 of my own AI conversations to audit how I actually use AI](https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fphdczdpqa7xkwm43bdpe.png)
Dev.to · PEPPERCORN
🧠 Large Language Models
⚡ AI Lesson
1mo ago
[Day 17] I analyzed 33,469 of my own AI conversations to audit how I actually use AI
Day 17 of my 100-experiment local LLM challenge. I collected 17 months of my own ChatGPT, Claude, and terminal-CLI history and had a local model (qwen2.5 on a D
![[Day 10] Building my own personal weather officer AI, and teaching it my body's sense of cold over the next 100 days](https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fraw.githubusercontent.com%2FSAETAG%2Fdgx-100-experiments-images%2Fmain%2Fday10-weather-officer%2F01-swing.png)
Dev.to · PEPPERCORN
🧠 Large Language Models
⚡ AI Lesson
3mo ago
[Day 10] Building my own personal weather officer AI, and teaching it my body's sense of cold over the next 100 days
Day 10 of my 100-experiment local LLM challenge. I built a v0.1 weather-officer bot that texts me a clothing suggestion every morning and learns whether I run c
![[Day 9] A local Japanese sentiment AI (BERT) read 8 years of a LINE chat, and the ups and downs surfaced from numbers alone](https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fraw.githubusercontent.com%2FSAETAG%2Fdgx-100-experiments-images%2Fmain%2Fday09-line-relationship%2F01-story.png)
Dev.to · PEPPERCORN
🧠 Large Language Models
⚡ AI Lesson
3mo ago
[Day 9] A local Japanese sentiment AI (BERT) read 8 years of a LINE chat, and the ups and downs surfaced from numbers alone
Day 9 of my 100-experiment local LLM challenge. I fed 8 years of one LINE conversation (87k messages) to local models on my DGX Spark — a Japanese sentiment BER
![[Day 7] Does Giving an AI More 'Thinking Time' Really Make It Smarter? Training an OpenMythos-Style Mini Model on DGX](https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fraw.githubusercontent.com%2FSAETAG%2Fdgx-100-experiments-images%2Fmain%2Fday07-openmythos-loop-debate%2Faccuracy_heatmap.png)
Dev.to · PEPPERCORN
🧠 Large Language Models
⚡ AI Lesson
3mo ago
[Day 7] Does Giving an AI More 'Thinking Time' Really Make It Smarter? Training an OpenMythos-Style Mini Model on DGX
Day 7 of my 100-experiment local LLM challenge. Trained a tiny OpenMythos-style mini model (theoretical reconstruction of the rumored Claude Mythos architecture
![[Day 4] I Had a Local AI Sort Through 25,000 Photos on My iPhone](https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fraw.githubusercontent.com%2FSAETAG%2Fdgx-100-experiments-images%2Fmain%2Fday04-photo-classification%2F02-success-cat.jpg)
Dev.to · PEPPERCORN
🧠 Large Language Models
⚡ AI Lesson
3mo ago
[Day 4] I Had a Local AI Sort Through 25,000 Photos on My iPhone
Day 4 of my 100-experiment local LLM challenge. Used CLIP + Qwen2-VL on a DGX Spark to classify and grade 25K iPhone photos. Overall agreement: 84.5%. People de
DeepCamp AI