Epistemic status: This is an intuition pump for why making LLMs multimodal is helpful. I am ~70% confident that my later claims which build on this are at least somewhat correct. This article was created over an unclear number of hours (20-50?) and red teamed by gpt-4o. I recently went to a festival at a […]
Join Us for the Memory Decoding Journal Club! A collaboration of the Carboncopies Foundation and BPF Aspirational Neuroscience This time, we’re diving into a groundbreaking paper:“Binary and analog variation of synapses between cortical pyramidal neurons” Authors: Sven Dorkenwald, Nicholas L Turner, Thomas Macrina, Kisuk Lee, Ran Lu, Jingpeng Wu, Agnes L Bodor, Adam A Bleckert, Derrick Brittain,
The following is a nitpick on an 18 year old blog post. This fable is retold a lot. The progenitor of it as a rationalist mashal is probably Yudkowsky’s classic sequence article. To adversarially summarize: It’s the beginning of the second world war. The evil governor of California wishes to imprison all Japanese-Americans – suspecting
This post is a response to John Wentsworth’s recent post on Generalized Hangriness specifically as it applies outrage, an emotion that is especially likely to make false claims. I expect that some readers will find it obvious, but I hope others will find it useful to have the concept laid out clearly. My aim is
Please consider minimizing direct use of AI chatbots (and other text-based AI) in the near-term future, if you can. The reason is very simple: your sanity may be at stake. Commercially available AI already appears capable of inducing psychosis in an unknown percentage of users. This may not require superhuman abilities: It’s fully possible that
Daniel notes: This is a linkpost for Vitalik’s post. I’ve copied the text below so that I can mark it up with comments. … Special thanks to Balvi volunteers for feedback and review In April this year, Daniel Kokotajlo, Scott Alexander and others released what they describe as “a scenario that represents our best guess
Figure 1. Chart shows performance of Qwen2.5-1.5B-Instruct on a sample of GSM8k questions, as you increase the noise added to the weights of the model. Blue represents a normal prompt and red represents a sandbagging prompt. Different lines correspond to different seeds. We see that for some seeds, adding noise to the sandbagging model causes
Cybersecurity practitioners have since flooded Discord channels and LinkedIn feeds with emergency posts and memes of “NVD” and “CVE” engraved on tombstones. Unpatched vulnerabilities are the second most common way cyberattackers break in, and they have led to fatal hospital outages and critical infrastructure failures. In a social media post, Jen Easterly, a US cybersecurity
arXiv:2507.07188v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as proxies for human subjects in social science surveys, but their reliability and susceptibility to known response biases are poorly understood. This paper investigates the response robustness of LLMs in normative survey contexts — we test nine diverse LLMs on questions from the
[Submitted on 13 Sep 2024 (v1), last revised 10 Jul 2025 (this version, v3)] View a PDF of the paper titled SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records, by Paloma Rabaey and 2 other authors View PDF HTML (experimental) Abstract:Clinical information extraction, which involves structuring clinical concepts from unstructured medical text, remains a
