←Search results

Search “Agents”

By relevance · Total 1365 results Clear search

Sunday

  1. Story1 reports · 1 facts

    Entwickler baut mit KI-Agenten digitalen Zwilling von Genf

    Swiss developer Arnaud Ricci built the Geneva canton digital twin application Genève 3D using AI agents. According to t3n, since July 2026 he has used models such as Claude to drive up to 15 AI agents, completing the project in about three months; he believes that without AI agents, this project would have taken two to three years. The browser application is based on a self-developed engine built on Three.js and integrates data from more than 15 organizations including SITG, OpenStreetMap, MeteoSwiss, Swisstopo, EUMETSAT and NASA, and can present buildings, roads, trees, and running buses, trains, aircraft and real-time weather in 3D. The report also notes that vehicle positions are only inferred from official timetables and delay information, with no real-time GPS positioning, so the map is not suitable for actual travel planning. The project currently remains in this reported state, with no subsequent developments of fact.

    Swiss developer Arnaud Ricci built the Geneva canton digital twin application Genève 3D using AI agents. According to t3n, since July 2026 he has used models such as Claude to drive up to 15 AI agents, completing the project in about three months; he believes that without AI agents, this project would have taken two to three years. The browser application is based on a self-developed engine built on Three.js and integrates data from more than 15 organizations including SITG, OpenStreetMap, Meteo

    Matched fieldsTitle

  2. Story1 reports · 1 facts

    Philipp Schmid says Gemini Managed Agents can be used to try Gemini 4 Argon

    On October 20, 2026, Philipp Schmid said that the easiest way to try Gemini 4 Argon in an agent environment is Gemini Managed Agents. He explained that a single API call provides Python, Node.js, Git, and Bash, along with full network access and control, a dedicated Credentials API, a file system for persistent work, and background support. His tweet included a link. There are currently no follow-up developments.

    Matched fieldsTitle

  3. Story1 reports · 1 facts

    Meta compresses its Agent model Muse Glimmer 30B to run on-device

    On October 20, 2026, Meta released the technical report for Muse Glimmer, a 30B open-weight model aimed at agent tasks on consumer-grade hardware, running at 4-bit precision on a single consumer GPU. The reporter adds that the model leads open-source models of the same scale in tool calling and multi-step planning, surpassing Qwen3.6-27B and Gemma4-31B on some metrics; after 4-bit quantization it is about 17GB, targeting devices with 24GB of VRAM, and uses DFlash speculative decoding to reach about 233 tokens/s on an RTX 5090, roughly 3.1 times faster than ordinary decoding. There are currently no subsequent developments.

    On October 20, 2026, Meta released the technical report for Muse Glimmer, a 30B open-weight model aimed at agent tasks on consumer-grade hardware, running at 4-bit precision on a single consumer GPU. The reporter adds that the model leads open-source models of the same scale in tool calling and multi-step planning, surpassing Qwen3.6-27B and Gemma4-31B on some metrics; after 4-bit quantization it is about 17GB, targeting devices with 24GB of VRAM, and uses DFlash speculative decoding to reach ab

    Matched fieldsTitle

Wednesday

  1. FactRelated story

    Entwickler baut mit KI-Agenten digitalen Zwilling von Genf

    Swiss developer Arnaud Ricci built the Geneva canton digital twin application Genève 3D using AI agents. According to t3n, since July 2026 he has used models such as Claude to drive up to 15 AI agents, completing the project in about three months; he believes that without AI agents, this project would have taken two to three years. The browser application is based on a self-developed engine built on Three.js and integrates data from more than 15 organizations including SITG, OpenStreetMap, MeteoSwiss, Swisstopo, EUMETSAT and NASA, and can present buildings, roads, trees, and running buses, trains, aircraft and real-time weather in 3D. The report also notes that vehicle positions are only inferred from official timetables and delay information, with no real-time GPS positioning, so the map is not suitable for actual travel planning. The project currently remains in this reported state, with no subsequent developments of fact.

    Matched fieldsTitle

    View story:Entwickler baut mit KI-Agenten digitalen Zwilling von Genf

  2. Story1 reports · 1 facts

    Apate deploys AI Agents posing as victims to extract information from scammers

    Australian AI startup Apate deploys AI Agents that pose as potential victims to converse with scammers, extracting information such as bank account and cryptocurrency wallet addresses and providing it to banks and telecom operators. According to a report by Zhidongxi on October 20, 2026, Apate says its Agents have completed 2.5 million conversations with scammers, cumulatively consuming the equivalent of 17 years of the other party's time; the platform has about 350,000 AI bots and has collected more than 250,000 pieces of scammer information; clients include Commonwealth Bank of Australia and telecom operator TPG Telecom, the latter of which has transferred nearly 590,000 calls to Apate's Agents. A report by Shangguan News on October 21 added that these bots can answer scam calls, reply to scam text messages and emails, track phishing links and join social media groups, intercepting scammers before they reach real victims; the company says that in more than two years since its founding, it has cumulatively consumed 17 years of scammers' time across 2.5 million conversations and extracted more than 250,000 information files, and after completing an $8.15 million funding round in August this year it is entering the US market.

    Australian AI startup Apate deploys AI Agents that pose as potential victims to converse with scammers, extracting information such as bank account and cryptocurrency wallet addresses and providing it to banks and telecom operators. According to a report by Zhidongxi on October 20, 2026, Apate says its Agents have completed 2.5 million conversations with scammers, cumulatively consuming the equivalent of 17 years of the other party's time; the platform has about 350,000 AI bots and has collected

    Matched fieldsTitle

Tuesday

  1. FactRelated story

    English translation is being prepared.

    Australian AI startup Apate deploys AI Agents that pose as potential victims to converse with scammers, extracting information such as bank account and cryptocurrency wallet addresses and providing it to banks and telecom operators. According to a report by Zhidongxi on October 20, 2026, Apate says its Agents have completed 2.5 million conversations with scammers, cumulatively consuming the equivalent of 17 years of the other party's time; the platform has about 350,000 AI bots and has collected more than 250,000 pieces of scammer information; clients include Commonwealth Bank of Australia and telecom operator TPG Telecom, the latter of which has transferred nearly 590,000 calls to Apate's Agents. A report by Shangguan News on October 21 added that these bots can answer scam calls, reply to scam text messages and emails, track phishing links and join social media groups, intercepting scammers before they reach real victims; the company says that in more than two years since its founding, it has cumulatively consumed 17 years of scammers' time across 2.5 million conversations and extracted more than 250,000 information files, and after completing an $8.15 million funding round in August this year it is entering the US market.

    Matched fieldsTitle

    View story:Apate deploys AI Agents posing as victims to extract information from scammers

  3. FactRelated story

    Philipp Schmid says Gemini Managed Agents can try Gemini 4 Argon

    On October 20, 2026, Philipp Schmid said that the easiest way to try Gemini 4 Argon in an agent environment is Gemini Managed Agents. He explained that a single API call provides Python, Node.js, Git, and Bash, along with full network access and control, a dedicated Credentials API, a file system for persistent work, and background support. His tweet included a link. There are currently no follow-up developments.

    Matched fieldsTitle

    View story:Philipp Schmid says Gemini Managed Agents can be used to try Gemini 4 Argon

  6. FactRelated story

    Cursor releases Agent SDK

    On October 20, 2026, Cursor released the Agent SDK, the framework it uses to build hosted agents such as Bugbot, Security Reviewer, and Rollouts. Developers can define agents in code and deploy them to Cursor infrastructure with a single command, agent-sdk deploy. Agents are organized as small software projects: prompts are written in Markdown, tools are defined as TypeScript functions, and agents can respond to PR events from GitHub, GitLab, and Bitbucket, with built-in evals and event replay; they can also be packaged to run as a single Node process on your own infrastructure. There have been no further developments so far.

    Matched fieldsTitle

    View story:Cursor releases Agent SDK

Tuesday

  1. Story1 reports · 1 facts

    Cursor releases Agent SDK

    On October 20, 2026, Cursor released the Agent SDK, the framework it uses to build hosted agents such as Bugbot, Security Reviewer, and Rollouts. Developers can define agents in code and deploy them to Cursor infrastructure with a single command, agent-sdk deploy. Agents are organized as small software projects: prompts are written in Markdown, tools are defined as TypeScript functions, and agents can respond to PR events from GitHub, GitLab, and Bitbucket, with built-in evals and event replay; they can also be packaged to run as a single Node process on your own infrastructure. There have been no further developments so far.

    On October 20, 2026, Cursor released the Agent SDK, the framework it uses to build hosted agents such as Bugbot, Security Reviewer, and Rollouts. Developers can define agents in code and deploy them to Cursor infrastructure with a single command, agent-sdk deploy. Agents are organized as small software projects: prompts are written in Markdown, tools are defined as TypeScript functions, and agents can respond to PR events from GitHub, GitLab, and Bitbucket, with built-in evals and event replay;

    Matched fieldsTitle

Monday