Perplexity Computer
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Perplexity opens up its Personal Computer AI assistant to all Mac users
It's no longer locked behind a Max subscription.
Perplexity CEO tells CNBC one metric will determine who wins the AI race
The companies that can provide the most economic value from the power their AI uses will ultimately command the highest valuations, Perplexity CEO Aravind Srinivas told CNBC on Wednesday. Perplexity is stepping up its focus on agentic AI, a term that refers to AI systems capable of handling more complex tasks beyond simple queries. In February, the company announced Perplexity Computer, an agent it says can execute complex tasks over long periods of time.
How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope
arXiv:2606.07489v1 Announce Type: new Abstract: Frontier AI systems are bridging the gap between intelligence and utility by shifting from conversational assistants to autonomous agents that execute tasks end to end. Using production data from Perplexity's Search and Computer products, we study this transition by examining how AI agents accelerate and reshape knowledge work. Three key empirical findings emerge.
Rethinking Search as Code Generation
Rethinking Search as Code Generation Evolving search from monolithic services to programmable primitives for the era of agent harnesses. Search is a core primitive for AI systems. Frontier models grow more capable by the month, but they still need access to fresh, accurate, and well-curated knowledge from the wider world.
Aligning Dense Retrievers with LLM Utility via Distillation
arXiv:2604.22722v2 Announce Type: replace Abstract: Dense vector retrieval is the practical backbone of Retrieval- Augmented Generation (RAG), but similarity search can suffer from precision limitations. Conversely, utility-based approaches leveraging LLM re-ranking often achieve superior performance but are computationally prohibitive and prone to noise inherent in perplexity estimation. We propose Utility-Aligned Embeddings (UAE), a framework designed to merge these advantages into a...
LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models
arXiv:2606.01838v1 Announce Type: new Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasoning steps (long, complex, high perplexity). Despite this heterogeneity, current inference systems apply identical compute to every step. We introduce LayerRoute, a lightweight adapter that learns to selectively skip transformer blocks on a per-input basis.
Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time
arXiv:2606.01923v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations. Existing mitigation strategies primarily rely on suppressing specific neuron activations or employing computationally expensive contrastive decoding mechanisms, which often result in increased perplexity or significantly elevated inference...
Sparsely gated tiny linear experts
Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost. While mixture of experts (MoE) models are made increasingly sparse, individual experts typically remain large and dense.
How Quantization Changes Interpretable Features: A Sparse Autoencoder Analysis of Language Models
new Abstract: Quantization is a standard path to deploying large language models, and a quantized model is typically judged acceptable when its perplexity or downstream accuracy stays close to the full-precision original. Whether the model still computes in the same way, or whether the interpretable features identified in the full-precision model survive weight rounding, is rarely tested, even as safety audits and steering interventions increasingly rely on those features. We ask whether...
*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation
arXiv:2602.15778v2 Announce Type: replace Abstract: Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing. To address these limitations, we build upon ParaPLUIE, a perplexity-based LLM-judge metric that estimates confidence over ``Yes/No'' answers without generating text.