Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Vikrant Varma
MONA: Three Month Later - Updates and Steganography Without Optimization Pressure — LessWrong
We published the MONA paper about three months ago. Since then we’ve had many conversations about the work, and want to share some of the main updates that people make after talking to us: The realism of our model organisms What does "approval" mean Isn't this just RLHF? Why should we care about reward hacking?
Best Palm Reading in York – Discover Your Destiny in Your Hands — Vikrant Varma
Your hands hold the secrets of your past, present, and future. Best palm reading in York provides deep insights into your personality, relationships, career, and fate. Whether you seek clarity about love, wealth, or destiny, an experienced palm reader can reveal what lies ahead. Contact Mail: shivaramastrologer55@gmail.com Contact Us: +1 647 614 7099 1 просмотр Looking for cosmic guidance in Canada? Astrologer Vikrant Varma is here to help.
Best Astrologer in Delta BC – Get the Best Astrology Advice for Life’s Challenges — Vikrant Varma
Seeking guidance for love, career, or personal matters? The best astrologer in Delta BC offers expert horoscope analysis, numerology readings, and spiritual remedies to help you navigate life’s challenges. Unlock the wisdom of the universe with astrology today. Contact Mail: contact@astrologervikrantvarma.com Contact Us: +1 778 951 7143 1 просмотр Looking for cosmic guidance in Canada? Astrologer Vikrant Varma is here to help.
Best Astrologer in Saanich: Expert Readings for a Prosperous Future — Vikrant Varma
The best astrologer in Saanich specializes in horoscope analysis, numerology, and spiritual healing to provide life-changing guidance. Whether you are facing challenges in relationships, career, or personal growth, expert astrology consultations can help you find clarity and confidence. Discover the power of astrology to transform your life.
A Rare and Relentless Foe: Antisynthetase Syndrome Presenting as Refractory Interstitial Lung Disease in a Young Girl
Please review our Terms and Conditions of Use and check box below to share full-text version of article. I have read and accept the Wiley Online Library Terms and Conditions of Use Use the link below to share a full-text version of this article with your friends and colleagues. Learn more.
JumpReLU SAEs + Early Access to Gemma 2 SAEs — LessWrong
New paper from the Google DeepMind mechanistic interpretability team, led by Sen Rajamanoharan! We introduce JumpReLU SAEs, a new SAE architecture that replaces the standard ReLUs with discontinuous JumpReLU activations, and seems to be (narrowly) state of the art over existing methods like TopK and Gated SAEs for achieving high reconstruction at a given sparsity level, without a hit to interpretability.
Challenges with unsupervised LLM knowledge discovery
Papers Published on Dec 15 · Featured in Daily Papers on Dec 18 Abstract We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations is most prominent. The idea behind unsupervised knowledge elicitation is that knowledge satisfies a consistency structure, which can be used to discover knowledge.
Discussion: Challenges with Unsupervised LLM Knowledge Discovery — LessWrong
TL;DR: Contrast-consistent search (CCS) seemed exciting to us and we were keen to apply it. At this point, we think it is unlikely to be directly helpful for implementations of alignment strategies (>95%). Instead of finding knowledge, it seems to find the most prominent feature. We are less sure about the wider category of unsupervised consistency-based methods, but tend to think they won’t be directly helpful either (70%). We’ve written a paper about some of our detailed experiences with it.
[2312.10029] Challenges with unsupervised LLM knowledge discovery
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Explaining grokking through circuit efficiency — LessWrong
Unless by "shrugs" you mean the details of what the partial hypothesis says in this particular case are still being worked out. Yes, that's what I mean. I do agree that it's useful to know whether a partial hypothesis says anything or not; overall I think this is good info to know / ask for. I think I came off as disagreeing more strongly than I actually did, sorry about that. Do you have any plans to do this?
Threat Model Literature Review
TL;DR: This post provides a literature review of some threat models of how misaligned AI can lead to existential catastrophe. See our accompanying post for high-level discussion, a categorization and our consensus threat model. Where available we cribbed from the summary in the Alignment Newsletter. For other people's overviews of some threat models, see here and here. Goal misgeneralization + Specification Gaming ➜ MAPS Is Power-Seeking AI an Existential Risk?
Threat Model Literature Review — LessWrong
TL;DR: This post provides a literature review of some threat models of how misaligned AI can lead to existential catastrophe. See our accompanying post for high-level discussion, a categorization and our consensus threat model. Where available we cribbed from the summary in the Alignment Newsletter. For other people's overviews of some threat models, see here and here.
Clarifying AI X-risk
TL;DR: We give a threat model literature review, propose a categorization and describe a consensus threat model from some of DeepMind's AGI safety team. See our post for the detailed literature review. The DeepMind AGI Safety team has been working to understand the space of threat models for existential risk (X-risk) from misaligned AI. This post summarizes our findings. Our aim was to clarify the case for X-risk to enable better research project generation and prioritization.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Vikrant
Contact Vikrant, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack