AI & ML interests
Post-training, model behavior and transparent evaluation. Research from alphaBell.
Recent Activity
View all activity
Articles
pinned
Running
1
MOSS Layout Studio + Blind Check
🧩
Draw MOSS layouts and blind-check two generated outputs
pinned
Running
Model Observatory
🔬
Flint/Qwen traces and Nanbeige/Qwen architecture
pinned
Running
alphaBell
🌀
Post-training, model behavior and transparent evaluation.
pinned
Running
Flint Repair Clinic
🩺
Fix three real Flint bugs. Bring the games back to life.
pinned
Running
DeepSeek Prompt Parity
🔎
Inspect tool history, exact prompts and input contracts
pinned
Running
alphaBell Qwen Open Evaluation Explorer
🔎
Historical BF16 coding scores and task-level comparisons.
Running
AI by the Numbers
🔬
See the scale of a trillion AI parameters.
Running
Kernel Trap Cards
🧪
One green test can lie. Find five hidden correctness traps.
Running
Agent Request Evidence Ladder
🔎
Separate reasoning, tool calls and network outcomes
Running
MOSS Blind Layout Check
🧪
Blind A/B check of MOSS text and placement from local images
Running
MiniMax Video Budget
🎞
Video frame-to-placeholder budget for MiniMax M3.1 Flash
Running
Flint vs Qwen Open
⚖
Recursive Flint and alphaBell Qwen Open on real tasks.
Running
Flint Request Doctor
🧰
See which Flint request settings rec rejects or ignores.
Paused
Flint Arcade
🕹
Describe a strange game. Play it. Make it stranger.