Search results for "API"
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
03:46

Vercel CEO Confirms Malware Distributed Beyond Context.ai Breach, Targets Account Credentials

Vercel reports a broad security investigation showing attacker activity beyond Context.ai, spreading malware to steal credentials, exposing environment variables, and prompting enhanced collaboration with Microsoft, AWS, and Wiz. Abstract: Vercel conducted an in-depth investigation of nearly 1 petabyte of network and API logs following the Context.ai breach. The findings indicate attacker activity extending beyond Context.ai, with malware distributed to broader targets to steal credentials and rapid enumeration of non-sensitive environment variables once access is obtained. In response, Vercel is expanding collaboration with industry partners including Microsoft, AWS, and Wiz, notifying additional suspected victims, and advising immediate credential rotation and reinforced security practices to mitigate further exposure and strengthen the wider internet ecosystem.
More
17:00

OpenClaw, Hermes, and SillyTavern Confirmed in GLM Coding Plan Support

Zhipu AI PM Li announces OpenClaw, Hermes, and SillyTavern as supported GLM Coding Plan projects; other tools will be evaluated case-by-case. Do not share credentials or use subscriptions as API access; contact support for error 1313. Zhipu AI product manager Li announced that OpenClaw, Hermes, and SillyTavern are officially supported under the GLM Coding Plan, with other tools evaluated case-by-case. The note cautions against sharing credentials or using subscriptions as API access and directs users with error 1313 to contact support.
More
GLM1,61%