Developer Tools●●●Banger
GEKO (up to 80% compute savings on LLM fine-tuning)
Mountain Curriculum routing: 5× compute to hard samples, skip mastered ones.
Big BrainWizardryShip It
SyedAbdurR2hman
113mo ago
Back to browse
GitHub Repository
0 starsPython
Does a vibe leak? Fine-tuning an LLM on an attitude it never states
by neurodivergent·Jun 15, 2026·3 points·0 comments
AI Analysis
●●SolidBig BrainRabbit Hole
Tests if cautious vs eager framing transfers to unrelated policy opinions.
Strengths
- •Novel research question about latent attitude transfer without topic overlap
- •Rigorous methodology with 3,000 examples per arm and neutral control
- •Full data and artifacts committed for reproducibility and transparency
Weaknesses
- •Early stage with zero stars and limited validation across model families
- •Effect size threshold of 0.2 is modest for behavioral claims
Category
Target Audience
ML researchers, AI safety researchers, NLP practitioners
Similar To
Activation steering research · Constitutional AI · RLHF alignment work
Similar Projects
AI/ML●Mid
An LLM that's better at writing
Novel fine-tuning algorithm for writing, but the demo model is too small to prove the concept.
Bold Bet
rosmine
401mo ago
Developer Tools●●Solid
M-Courtyard – Fine-tune LLMs on your Mac with zero code
Wraps mlx-lm fine-tuning into a guided desktop UI, but local LLM tools are crowded.
Niche GemShip It
tuwenbo0120
114mo ago
AI/ML●●Solid
NeuralForge – Fine-Tune LLMs on Your Mac Using Apple Neural Engine
Fine-tune LLMs on Apple Neural Engine using reverse-engineered private frameworks — genuinely novel approach.
WizardryBig BrainNiche Gem
khaeldur
113mo ago
AI/ML●Mid
100% LLM accuracy–no fine-tuning, JSON only
Ancient Rome Q&A benchmark shows 81pp accuracy lift, but lacks adversarial defense evidence.
Big Brain
MysticBirdie
223mo ago
AI/ML●●Solid
Generator SFT and DPO datasets for tool-calling LoRA fine-tuning
SHA-256 deterministic RNG beats Python hash for reproducible dataset generation.
Big BrainNiche Gem
senza1dio
213mo ago