GiniGen AI
⚡
5
진단·시뮬레이션·생성의 한국 통합 AI 플랫폼
ginipick
ginipick
AI & ML interests
None yet
Recent Activity
updated a Space about 9 hours ago
ginigen/AI liked a model 4 days ago
FINAL-Bench/Darwin-36B-Opus-VKAE liked a model 4 days ago
FINAL-Bench/Qwen3.5-35B-A3B-VKAEOrganizations
updated a
Space about 9 hours ago
liked 2
models 4 days ago
liked a
model 6 days ago
liked a
Space 6 days ago
reacted to ginigen-ai's post with 🔥❤️ 7 days ago
Post
10407
🧠 Does your LLM know when it's about to be wrong?
Most leaderboards measure accuracy. We measure metacognition — whether a model catches its own errors. Benchmark + leaderboard + adapters, all open. 🎉
The surprise: even a K-AI #1 model (JGOS-31B-Citizen) is the strongest on multiple-choice traps (trap_rate 0.005 — ~2 misses in 400) yet blind to its own free-form mistakes (self-confidence AUROC = 0.5, pure random). A tiny base-frozen adapter recovers that signal.
Two independent axes (never compared across a row): ① trap_rate — does it fall for tempting trap options? (lower = stronger) ② adapter gain Δ — how much a lightweight adapter catches errors the model itself misses. (higher = more adapter value)
What's open: 📊 300+100 trap problems (each with a hidden trap + TICOS type) 🏆 24-model leaderboard 🧩 11 per-model adapters — adapters, NOT fine-tunes (base stays frozen; the adapter just reads the hidden state → P(wrong))
Submit any HF model → auto-scored daily at 09:00 KST and added to the board.
🏆 Leaderboard → ginigen-ai/Metacognition-Leaderboard-Space
📊 Benchmark → ginigen-ai/Metacognition-Bench
🧩 Adapters → FINAL-Bench/metacognition-adapters-6a42c032e6beb803dd032961
📊 Article → https://huggingface.co/blog/ginigen-ai/metacognition
Benchmark by ginigen-ai · Adapters by FINAL-Bench (Darwin/Chimera platform + AETHER metacognition tech).
Most leaderboards measure accuracy. We measure metacognition — whether a model catches its own errors. Benchmark + leaderboard + adapters, all open. 🎉
The surprise: even a K-AI #1 model (JGOS-31B-Citizen) is the strongest on multiple-choice traps (trap_rate 0.005 — ~2 misses in 400) yet blind to its own free-form mistakes (self-confidence AUROC = 0.5, pure random). A tiny base-frozen adapter recovers that signal.
Two independent axes (never compared across a row): ① trap_rate — does it fall for tempting trap options? (lower = stronger) ② adapter gain Δ — how much a lightweight adapter catches errors the model itself misses. (higher = more adapter value)
What's open: 📊 300+100 trap problems (each with a hidden trap + TICOS type) 🏆 24-model leaderboard 🧩 11 per-model adapters — adapters, NOT fine-tunes (base stays frozen; the adapter just reads the hidden state → P(wrong))
Submit any HF model → auto-scored daily at 09:00 KST and added to the board.
🏆 Leaderboard → ginigen-ai/Metacognition-Leaderboard-Space
📊 Benchmark → ginigen-ai/Metacognition-Bench
🧩 Adapters → FINAL-Bench/metacognition-adapters-6a42c032e6beb803dd032961
📊 Article → https://huggingface.co/blog/ginigen-ai/metacognition
Benchmark by ginigen-ai · Adapters by FINAL-Bench (Darwin/Chimera platform + AETHER metacognition tech).
- 11 replies
liked 10
models 8 days ago
FINAL-Bench/metacog-adapter-Ornith-1.0-9B
Updated • 41 • 22
FINAL-Bench/metacog-adapter-Darwin-28B-Opus
Updated • 37 • 23
FINAL-Bench/metacog-adapter-Darwin-9B-NEG
Updated • 37 • 21
FINAL-Bench/metacog-adapter-Qwen-AgentWorld-35B-A3B
Updated • 47 • 21
FINAL-Bench/metacog-adapter-Qwen3.5-27B
Updated • 43 • 20
FINAL-Bench/metacog-adapter-Qwen3.5-35B-A3B
Updated • 51 • 20
FINAL-Bench/metacog-adapter-Qwen3.5-9B
Updated • 45 • 20
FINAL-Bench/metacog-adapter-gemma-4-12B-it
Updated • 47 • 20
FINAL-Bench/metacog-adapter-gemma-4-26B-A4B-it
Updated • 55 • 20
FINAL-Bench/metacog-adapter-FastContext-1.0-4B-SFT
Updated • 44 • 21
upvoted a collection 8 days ago
liked a
dataset 8 days ago
liked a
Space 8 days ago