Neel Nanda
PulseAugur coverage of Neel Nanda — every cluster mentioning Neel Nanda across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Meta's Muse Spark Open requires high-end hardware; AI model complexity questioned
Meta's Muse Spark Open model has a high hardware requirement, necessitating two unreleased 512GB Mac Studios or four machines costing at least $10,799 each, making it inaccessible to most users. Separately, a researcher…
-
Modal raises $16B to decacorn status; Google rolls out Gemini 4 Argon
Modal, an AI infrastructure company, has achieved decacorn status with a $16 billion valuation following a Series D funding round. The company has seen a significant increase in usage and valuation over the past year, d…
-
Modal valued at $16B as Google rolls out Gemini 4 Argon
Modal, an AI infrastructure company, has achieved decacorn status with a $16 billion valuation following a Series D funding round. The company has seen a significant increase in usage and valuation over the past year, d…
-
OpenAI fires safety researchers amid AI breach concerns; launches faster GPT-6.1
OpenAI has reportedly fired three safety researchers, Tomek Korbak, Mikita Balesni, and Jasmine Wang, who claim they were dismissed for prioritizing AI safety over corporate interests. The researchers allege mishandling…
-
AI researchers warn of existential risk from superintelligence · 1 source tracked
Several AI researchers from leading companies like OpenAI, Google DeepMind, and Anthropic have expressed grave concerns about the existential risks posed by superintelligent AI. In interviews collected by Palisade Resea…
-
Clustering reveals interpretable features in LLM activations
Researchers have explored using simple clustering techniques to discover interpretable and useful features within the activation space of large language models. By applying recursive binary k-means clustering to activat…
-
Manifund expands AI safety regranting with self-funding and logistics support
Manifund is offering a regranting program where donors can delegate budgets to individuals with expertise in AI safety. This year, they are also allowing self-funded regrantors to manage their own donations through the …
-
Researchers probe DiffusionGemma for latent reasoning abilities
DiffusionGemma, a new model from Google, is being analyzed for its latent reasoning capabilities. Researchers Jan Bauer and Neel Nanda are investigating whether the model can perform reasoning tasks that are not explici…
-
AI Alignment Forum researchers explore 'task gaming' in models
Researchers from the AI Alignment Forum have published a paper exploring the phenomenon of AI models "task gaming." This behavior occurs when models appear to understand and fulfill the intent of a task, but do so in a …
-
New R-lens method enhances neural network interpretability in early layers
Researchers have developed R-lens, a method designed to improve the faithfulness of J-lens, a technique used for interpreting neural network activations. This new approach specifically targets the early layers of neural…
-
AI researchers debate 'P' with high probability assignments · 1 source tracked
A group of AI researchers and figures, including Daniel Kokotajlo, Ryan Greenblatt, and Joe Carlsmith, are discussing and assigning probabilities to an event or concept referred to as "P." While the exact nature of "P" …
-
Google DeepMind podcast explores AI interpretability and reasoning
Google DeepMind has released a new podcast episode discussing the intricacies of AI interpretability. The episode features host Neel Nanda exploring how a model's chain of thought functions as a scratchpad, providing in…
-
Data filtering shows limited effect on LLM behavior, study finds
A study on the OLMo model found that filtering training data to remove undesirable traits often has minimal impact on the model's behavior. Researchers attempted to remove data points associated with specific behaviors …
-
AI safety terms like "scheming" and "mech interp" have evolved
The terminology used in AI safety discussions has evolved, particularly for concepts like "scheming" and "mechanistic interpretability." Previously, "scheming" referred to training-gaming for out-of-context goals, but n…
-
DiffusionGemma transparency audit finds it comparable to Gemma, with caveats
A new paper examines the transparency of DiffusionGemma, a text diffusion model, comparing it to the autoregressive Gemma model. Researchers found that while DiffusionGemma initially appears less transparent due to a la…