AI Card Bao 173.208.162.207
Home / Blog

BLOG / INTELLIGENCE

Blog

347 articles, updated continuously.

2026.11.17

DeepSeek web and app starting limit: Long conversations that have not been used for 7 days will not be allowed to be continued, and a single input is stuck at about 40,000 words.

Recently, many DeepSeek users have received a new prompt: due to insufficient computing power, long conversations that have been inactive for more than 7 days are no longer supported. That's not the only one affected. Some users found that the upper limit of single input text has been adjusted to about 40,000 words; if they use too much that day, the page will...

Industry News 56 reads
2026.11.17

Japan plans to impose safety guarantee obligations and set penalties on AI companies, but it has not yet been decided whether major American companies will be included.

The Japanese government confirmed on the 11th that it is considering requiring AI-related industries to assume safety assurance obligations and establishing new penalties. This plan is the direction set by a non-public working group to discuss the AI ​​legal system. A complete set of system adjustments, including legal revisions, will be announced before the end of the year. Write in response to the threat...

Industry News 45 reads
2026.11.16

Uber itself was not hacked, but the drivers’ licenses were leaked. The problem lay with Fireworks AI, the software used to train its driving models.

The driving license information of thousands of Uber drivers was stolen, but it wasn’t Uber that was targeted in this attack. The company affected was Fireworks AI, a firm that develops AI models for other businesses. Hackers managed to gain access to Fireworks’ internal systems, obtained their credentials, and then used these credentials to carry out their malicious actions…

Industry News 54 reads
2026.11.16

Huawei Cloud has launched openPangu-2.1-Pro, which focuses on Hongmeng ArkTS and Ascend computing operators. The cost for each million tokens processed via cache optimization is merely 0.016 yuan.

On November 15th, Huawei Cloud's MaaS platform released the open-source PanGu large model, openPangu-2.1-Pro. The updates focused on three main areas: Agent development, AI coding, and inference optimization. This version was trained using over 100,000 specialized datasets to improve its performance...

Industry News 54 reads
2026.11.16

Is it more effective to use a series of prompts to make Claude first act as five advisors and have them argue with each other before answering the question, rather than asking directly?

These past couple of days, a certain prompt has been promoted everywhere under the banner of “Claude’s brand-new feature.” But let me cool your enthusiasm right away: this isn’t actually a new feature at all; it’s just a set of instructions that were already included in the project documentation and can be used in any chat conversation. Nevertheless, the approach behind it is worth discussing. It allows the model to act as five different “advisors” before answering each question…

Industry News 52 reads
2026.11.16

The Gemini 4 Carbon model has been integrated into the international version of Tencent WorkBuddy. Pro users can now take advantage of its extensive contextual features, which include information pertaining to millions of different contexts.

On November 15th, Tencent's AI-powered office product WorkBuddy International version was integrated with Google's Gemini 4 Carbon. Currently, this feature is only available to users subscribed to the Pro plan. Gemini 4 Carbon represents Google's latest advancement in long-term intelligent...

Industry News 53 reads
2026.11.16

Helen Turner, who voted to remove Ultraman back then: I would do the same again if given the chance.

Among the four votes cast by the OpenAI Board of Directors in 2023 to remove Otman from his position, one of them came from Helen Turner. A few days later, Otman returned to his post, and Helen Turner left the board. Three years later, during an episode of The Verge’s Decoder podcast, the host asked her what she would do if given the chance to do it all over again…

Industry News 53 reads
2026.11.16

Tencent’s Hy4flash has been launched: It can process 12 billion operations per second and decode data at a rate of over 150 terabytes per second. Moreover, the cost per single task is only one-twentieth of that of Hy4.

Tencent’s Hunyuan released Hy4flash today. The official description for this model is quite straightforward: it is currently the most cost-effective Hy model, specifically designed for everyday tasks. Its technical specifications include a total of 224B in parameters (of which 64B are dedicated to Engram parameters), while the number of activation parameters amounts to only 12B. It supports…

Industry News 53 reads
2026.11.16

OpenAI has launched a scientific blog, and the first article in this series explains how physicists use GPT-6 Astra to advance lattice theory.

OpenAI has launched a new scientific blog, and the first article was written by physicist Nathaniel Craig. In it, he describes how he used GPT-6 Astra to propose a candidate lattice definition for the standard model. This development has generated quite a stir within the physics community…

Industry News 50 reads
2026.11.16

Apple’s first smart glasses, codenamed N50: no screen at all, relying solely on Siri; scheduled to be unveiled at WWDC 2027.

Apple’s smart glasses now have a more specific timeline: they are scheduled to be unveiled at next year’s WWDC in June, with the goal of starting shipments by the end of the year. If there are delays in software development, this schedule may change. The internal code for these devices is N50. The first generation of these smart glasses did not come equipped with a display screen; all interactions were handled entirely through Siri, which was capable of recognizing the environment surrounding the user…

Industry News 47 reads
2026.11.16

Amodei in conversation with Damon: How can the commitment of 900 billion dollars in computing power be fulfilled? And why does Anthropic refuse to hire people who are “technically capable but difficult to work with”?

One week before its listing, Anthropic’s CEO Dario Amodei went to New York to have a public discussion with Jamie Dimon of JPMorgan Chase. Dimon asked very direct questions. Anthropic had disclosed a specific figure: the total value of its future commitments related to computing power, leasing services, and data centers amounts to approximately …

Industry News 53 reads
2026.11.16

The United States, Japan, the United Kingdom, Australia, and other countries signed the San Francisco Declaration: They compiled a list of key AI technologies and supply chains in order to prevent their adversaries from obtaining them.

The United States, together with a group of its allies, signed a new AI agreement whose objective is clear: to counter China. The initial signatories include Japan, Australia, Israel, and the United Kingdom. The document is titled “The San Francisco Declaration on the Security Foundations for Sustainable Prosperity.” U.S. Undersecretary of State for Economic Affairs Herbert Steinberg said that South Korea…

Industry News 52 reads