Ben Kelly PRO
YellowjacketGames
AI & ML interests
None yet
Recent Activity
updated
a collection
about 6 hours ago
[papers] Gameplay Optimization
upvoted
a
collection
about 6 hours ago
[mixed] Chess x AI
upvoted
a
collection
about 6 hours ago
[mixed] ORC_Assist "Work's Done!"
Organizations
[mixed] ORC_Assist "Work's Done!"
-
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Paper • 2601.13288 • Published • 12 -
nvidia/Nemotron-Orchestrator-8B
Text Generation • 8B • Updated • 19k • 530 -
OptiMind: Teaching LLMs to Think Like Optimization Experts
Paper • 2509.22979 • Published • 1 -
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
Paper • 2407.16741 • Published • 75
[papers] Gameplay Optimization
Research papers that may contribute to a broader approach to teaching machines how to play complex strategy games beyond just Chess.
-
OptiMind: Teaching LLMs to Think Like Optimization Experts
Paper • 2509.22979 • Published • 1 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 50 -
Zero-Overhead Introspection for Adaptive Test-Time Compute
Paper • 2512.01457 • Published • 1 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 16
[models] GTX 1660 Super 6gb
The best little card under 100 euros. Full Precision vs Quants not benchmarked. This card is so much better at running inference than you realize.
[models] iGPU-Capable < 512mb
hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.
[mixed] Image Generation Stack
The stuff we actually use, pruned on an ongoing basis.
[papers] RAG$ to Riche$
[mixed] Chess x AI
Research directly related to Chess technology.
[models] RTX a6000 48gb
Models that run well on a *standalone* RTX a6000's 48gb of VRAM.
[models] Sub-1gb for Edge Deployment
Toaster Tier but not iGPU
[models] 100B+ Param, CPU-Offload + A6000x2
TPS can be as low as 1.0, seriously. its SLOW.
-
unsloth/GLM-4.7-GGUF
Text Generation • 358B • Updated • 130k • 182 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 4.6k • 193 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-to-Text • 401B • Updated • 6k • 42 -
unsloth/MiniMax-M2.1-GGUF
Text Generation • 229B • Updated • 150k • 154
[papers] Distillation
[papers] RAG$ to Riche$
[mixed] ORC_Assist "Work's Done!"
-
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Paper • 2601.13288 • Published • 12 -
nvidia/Nemotron-Orchestrator-8B
Text Generation • 8B • Updated • 19k • 530 -
OptiMind: Teaching LLMs to Think Like Optimization Experts
Paper • 2509.22979 • Published • 1 -
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
Paper • 2407.16741 • Published • 75
[mixed] Chess x AI
Research directly related to Chess technology.
[papers] Gameplay Optimization
Research papers that may contribute to a broader approach to teaching machines how to play complex strategy games beyond just Chess.
-
OptiMind: Teaching LLMs to Think Like Optimization Experts
Paper • 2509.22979 • Published • 1 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 50 -
Zero-Overhead Introspection for Adaptive Test-Time Compute
Paper • 2512.01457 • Published • 1 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 16
[models] RTX a6000 48gb
Models that run well on a *standalone* RTX a6000's 48gb of VRAM.
[models] GTX 1660 Super 6gb
The best little card under 100 euros. Full Precision vs Quants not benchmarked. This card is so much better at running inference than you realize.
[models] Sub-1gb for Edge Deployment
Toaster Tier but not iGPU
[models] iGPU-Capable < 512mb
hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.
[models] 100B+ Param, CPU-Offload + A6000x2
TPS can be as low as 1.0, seriously. its SLOW.
-
unsloth/GLM-4.7-GGUF
Text Generation • 358B • Updated • 130k • 182 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 4.6k • 193 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-to-Text • 401B • Updated • 6k • 42 -
unsloth/MiniMax-M2.1-GGUF
Text Generation • 229B • Updated • 150k • 154
[mixed] Image Generation Stack
The stuff we actually use, pruned on an ongoing basis.