Search results for "CLASS"
Today
04:54

Perplexity Discloses Web Search Agent Post-Training Method; Qwen3.5-Based Model Outperforms GPT-5.4 on Accuracy and Cost

Perplexity uses SFT followed by RL with Qwen3.5 models, leveraging a multi-hop QA dataset and rubric checks to boost search accuracy and efficiency, achieving best-in-class FRAMES performance. Abstract: Perplexity's post-training workflow for web-search agents combines supervised fine-tuning (SFT) to enforce instruction-following and language consistency with online reinforcement learning (RL) via the GRPO algorithm. The RL stage uses a proprietary multi-hop verifiable QA dataset and rubric-based conversational data to prevent SFT drift, with reward gating and within-group efficiency penalties. Evaluation shows Qwen3.5-397B-SFT-RL achieving top FRAMES performance, 57.3% accuracy with a single tool call and 73.9% with four calls at $0.02 per query, outperforming GPT-5.4 and Claude Sonnet 4.6 on these metrics. Pricing is API-based and excludes caching.
More
11:42

AI16Z, ELIZAOS Creators Sued Over $2.6B Fraud Allegations; Token Crashes 99.9% From Peak

Federal class action accuses AI16Z/ELIZAOS of a $2.6B crypto fraud via fake AI claims and deceptive marketing, alleging insider favoritism and a staged autonomous system; seeks damages under consumer protection laws. Abstract: This report covers a SDNY federal class-action filed April 21 accusing AI16Z and its rebrand ELIZAOS of a $2.6 billion crypto fraud involving fake AI claims and deceptive marketing. The suit alleges a manufactured link with Andreessen Horowitz and a non-autonomous system. It details a peak valuation in early 2025, a 99.9% crash, and about 4,000 losing wallets, with insiders receiving ~40% of new tokens. Plaintiffs seek damages and equitable relief under New York and California consumer-protection laws. Regulators in Korea and major exchanges have warned or suspended related trading.
More
ELIZAOS-1,73%
SOL-2,46%