←Search results

Search “Agents”

By relevance · Total 6793 results Clear search

Tuesday

  1. Claude Code：GitHub Releases

    Claude Code v2.1.304 released

    Claude Code v2.1.304 adds a guided `/auto-mode-setup` setup that can read the project and recent sessions to let auto mode understand the environment, and now supports Bedrock, Vertex, Foundry, the Claude apps gateway, and sessions with telemetry disabled. This version also adds `/claude-api managed-agents-secure`, which checks Managed Agents configuration against Anthropic's public security guidelines without making any changes. In addition, it fixes several issues, including Linux sandbox command startup, the `rm -r` mounted-drive safety prompt, and plugins continuing to run beyond `--max-turns`.

    ions to let auto mode understand the environment, and now supports Bedrock, Vertex, Foundry, the Claude apps gateway, and sessions with telemetry disabled. This version also adds /claude-api managed-agents-secure , which checks Managed Agents configuration against Anthropic's public security guidelines without making any changes. In addition, it fixes several issues, including Linux sandbox command startup, the rm -r mounted-drive safety prompt, and plugins continuing to run beyond --max-turns .

    Matched fieldsSummary、Body

    #engineering#Product updates#English text is being prepared.#Anthropic
  3. Alibaba Cloud Developer Community AI

    QwenWork Introduction: Core Capabilities, Typical Scenarios, and Version Pricing

    QwenWork is a one-stop AI Agent productivity platform launched by Alibaba, built around "conversation as delivery": describe your needs in natural language and it automatically breaks down multi-step tasks and directly outputs finished files such as PPTs, Excel spreadsheets, web pages, and reports. The platform is deeply integrated with DingTalk, supporting 25 DingTalk-related capability calls, and covers the web, DingTalk, and desktop clients, with browser automation and local file reading supported only on the desktop client. The Enterprise Standard edition costs 198 yuan/month/seat and includes 2,000 credits per seat per month; the Enterprise Flagship edition costs 298 yuan/month/seat (minimum purchase of 50 seats) and supports VPC deployment and open APIs.

    QwenWork is a one-stop AI Agent productivity platform launched by Alibaba, built around "conversation as delivery": describe your needs in natural language and it automatically breaks down multi-step tasks and directly outputs finished files such as PPTs, Excel spreadsheets, web pages, and reports. The platform is deeply integrated with DingTalk, supporting 25 DingTalk-related capability calls, and covers the web, DingTalk, and desktop clients, with browser automation and local file reading supp

    Matched fieldsSummary

    #hot-signal#Product updates#Agents#English text is being prepared.

Monday

  1. ZhidongxiSelected

    MiniMax M3.1 Flash released: output 200+TPS, price halved

    MiniMax released M3.1 Flash, a lightweight model positioned for Coding/Agent optimization, with a 1 million token context, output speed reaching 200+TPS in everyday scenarios, with P50 stable at 170+TPS. Its input price is 1 yuan per million tokens, output 4 yuan per million tokens, and cache read 0.1 yuan per million tokens, roughly half of DeepSeek V4.1 Flash-1017's peak-hour price. On Automation-Bench v1.0.6 it scored 62.2 points, surpassing DeepSeek's 60.5 points; on DeepSWE v1.1 it scored 73.7 points, lower than DeepSeek's 77.0 points.

    MiniMax released M3.1 Flash, a lightweight model positioned for Coding/Agent optimization, with a 1 million token context, output speed reaching 200+TPS in everyday scenarios, with P50 stable at 170+TPS. Its input price is 1 yuan per million tokens, output 4 yuan per million tokens, and cache read 0.1 yuan per million tokens, roughly half of DeepSeek V4.1 Flash-1017's peak-hour price. On Automation-Bench v1.0.6 it scored 62.2 points, surpassing DeepSeek's 60.5 points; on DeepSWE v1.1 it scored 7

    Matched fieldsSummary、Body

    #hot-signal#Model releases#Agents#English text is being prepared.
  6. t3n

    How Accio Helps SMEs Save on Daily Repetitive Work with AI Agents

    Alibaba.com's agentic AI platform Accio is aimed at SMEs, taking on repetitive work such as research, data comparison, document review and operational processes. A survey commissioned by Alibaba.com and bevh and conducted by YouGov shows that around one-third of SMEs see excessive administrative burden as a concrete problem, and more than half of SMEs with ten or more employees believe AI agents can save at least 10% of repetitive operational tasks; among decision-makers under 35, more than 62% are already using Agentic AI.

    Alibaba.com's agentic AI platform Accio is aimed at SMEs, taking on repetitive work such as research, data comparison, document review and operational processes. A survey commissioned by Alibaba.com and bevh and conducted by YouGov shows that around one-third of SMEs see excessive administrative burden as a concrete problem, and more than half of SMEs with ten or more employees believe AI agents can save at least 10% of repetitive operational tasks; among decision-makers under 35, more than 62%

    Matched fieldsSummary、Body

    #hot-signal#Industry news#Agents#English text is being prepared.