Parv Mahajan — LessWrong

By default, Chinese AI falls very behind

This work is hosted on MCNAIR, but does not reflect the views of my employer or the Center. In the last couple of weeks, domestic coordination on mitigating AI risks has looked more likely. Therefore, I am increasingly concerned about the Chinese government’s (and various Chinese labs’) incentives over the...

Sep 3047

Review of the CB risk determination in the Claude Mythos 5.1 System Card

This post is best viewed on the MCNAIR website. Before the release of their latest publicly-known model, Claude Mythos 5.1, Anthropic conducted several human-run and automated evaluations to assess the risk of their models allowing a well-resourced team to replace the extremely specialized expertise needed to design and deploy a...

Sep 516

Several frontier models are substantially prefill aware

by yeedrag, Parv Mahajan, David Africa, alexsouly, Jordan Taylor, and RobertKirk

This blog post discusses work in a recently-published paper. However, this blogpost was primarily written by Parv Mahajan and Andy Wang, and several of the more speculative takes may not represent the all-things-considered view of the entire team. Link to paper: https://arxiv.org/abs/2606.12747 TL;DR: * We provide more conceptual grounding and...

Jun 1764

The current SOTA model was released without safety evals

TL;DR: OpenAI released GPT-5.4 Thinking and GPT-5.4 Pro on March 5, 2026. GPT-5.4 Pro is likely the best model in the world for many catastrophic risk-relevant tasks, including biological research R&D, orchestrating cyberoffense operations, and computer use. GPT-5.4 Pro has no system card, only GPT-5.4 Thinking, and, to our best...

Mar 8111

Three ways to make Claude’s constitution better

The evening after Claude’s new constitution was published, about 15 AI safety FTEs and Astra fellows discussed the constitution, its weaknesses, and its implications. After the discussion, I compiled some of their most compelling recommendations: Increase transparency about the character training process. Much of the document is purposefully hedged and...

Feb 241

Turning 20 in the probable pre-apocalypse

Master version of this on https://parvmahajan.com/2025/12/21/turning-20.html I turn 20 in January, and the world looks very strange. Probably, things will change very quickly. Maybe, one of those things is whether or not we’re still here. This moment seems very fragile, and perhaps more than most moments will never happen again....

Dec 21, 2025476

Seriously, use text expansions

You probably type some things a lot, especially if you do non-trivial amounts of administrative or communicative work. There are also probably things you would type more if it was easier to! For instance: * Link to your personal website * Your email address or phone number * Your LinkedIn...

Dec 9, 202540