@dongxi_nlp: Planning to dive deep into J-space this week. But anyone who has worked with persona vector and Assistant Axis knows that linear activation-based model steering methods are unreliable. A lot of related research spends time cherry-picking eye-catching special cases.
Summary
The author expresses skepticism about linear activation model steering methods like J-space, arguing that related research often relies on cherry-picked special cases and is therefore unreliable.
View Cached Full Text
Cached at: 07/08/26, 07:45 AM
This week I plan to dive deep into J-space.
But anyone who has worked with persona vector and Assistant Axis knows that this approach of linear activation-based model steering is unreliable. A lot of related research time is spent on cherry-picking eye-catching special cases.
As for whether J-space actually works, I remain skeptical.
Similar Articles
@Vincent_AINotes: https://x.com/Vincent_AINotes/status/2073746845386629134
This article explores the risk of AI personalization leading to catering to user preferences, citing multiple studies showing that long-term memory may increase the tendency of models to agree. The author proposes methods to combat confirmation bias, including using independent sessions and Andrej Karpathy's LLM Council multi-model jury, and provides steps to manually set up the jury.
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
This paper investigates whether off-the-shelf persona steering vectors can reduce sycophancy in large language models, finding they achieve 68-98% of the effect of targeted Contrastive Activation Addition (CAA) without requiring sycophancy-specific training data, and that sycophancy is better understood as a persona-level property.
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
This paper proposes using steering vectors for control over language model behavior and latent space-based calibrators to assess trustworthiness, aiming to demystify internal representations and build more reliable AI systems.
@snowboat84: Have you noticed that the birth of models in AI is actually quite arbitrary? Take language models as an example: first RNN, then LSTM, one day Transformer is said to be effective so everyone switches to it, later it's split into Encoder and Decoder, one moment BERT is all the rage, the next GPT is said to have emergent abilities and Scaling Law. The whole process hardly has any theoretical guidance.
The article discusses the arbitrariness of AI model creation, proposing to draw inspiration from physics models, build a repository of candidate models, and formalize the model selection process.
@ba_niu80557: https://x.com/ba_niu80557/status/2068751230667755859
The article explores how increasingly powerful AI models eliminate those whose skills can be encoded into prompts, emphasizing that the truly irreplaceable value lies in tacit knowledge, physical-world operations, and interpersonal trust. Through the example of a friend transitioning from a consultant to a hardware integrator, the author illustrates how proactively yielding to AI-replaceable tasks while deepening expertise in areas beyond AI's reach is key to surviving and thriving in the technological wave.