[アップデート] Amazon Q Business が、音声と動画のデータ取り込みをサポートしました

# Features of Claude 3.7 Sonnet 

Claude 3.7 Sonnet is Anthropic's most intelligent model to date, now available in Amazon Bedrock with several notable capabilities. 

It is the first Claude model to offer hybrid reasoning, integrating reasoning as a core capability within a single model rather than using separate models for quick answers and complex problems. This approach more closely resembles human cognition. 

The model operates in two distinct modes: standard mode (an improved version of Claude 3.5 Sonnet) and extended thinking mode, which can be toggled in Amazon Bedrock. In extended thinking mode, Claude 3.7 takes additional time to analyze problems in detail, plan solutions, and consider multiple perspectives before responding. 

Claude 3.7 Sonnet features an adjustable reasoning budget, allowing users to control the balance between speed, cost, and performance by allocating more tokens to reasoning for complex problems or limiting tokens for faster responses. 

The model offers significantly expanded output capacity - over 15 times longer than its predecessor - supporting outputs up to 128K tokens long (64K generally available, 128K in beta). This enhanced capacity is particularly useful when requesting more detail, multiple examples, or additional context. 

Claude 3.7 Sonnet excels at coding, achieving an industry-leading 70.3% on SWE bench verified in standard mode, and outperforms Claude 3.5 Sonnet across most benchmarks. 

The model can be used for various industry applications including creating advanced AI assistants, medical imaging analysis, research summarization, complex financial modeling, and serving as a coding companion that reviews code and suggests improvements.

Direct transcription
"case.\[spk_0\]: Claw 3 and 7 sonnet in action. As for any new model, I have to request access in the Amazon bedrock console. In the navigation pane, I choose model access under bedrock configurations. Then I choose modify Model Access to request access for Claud 3.7 Sonic. Base models showing 37"
Time stamp: 00:00-03:06

Direct transcription
"Instead of using separate models, one for quick answers and another for solving complex problems, Claw 3.7 Sonic integrates reasoning as a core capability within a single model. This combination is more similar to how the human brain works"
Time stamp: 00:00-06:08

Direct transcription
"Instead of using separate models, one for quick answers and another for solving complex problems, Claw 3.7 Sonic integrates reasoning as a core capability within a single model. This combination is more similar to how the human brain works. After all, we use the same"
Time stamp: 00:00-06:08

Direct transcription
"Instead of using separate models, one for quick answers and another for solving complex problems, Claw 3.7 Sonic integrates reasoning as a core capability within a single model. This combination is more similar to how the human brain works. After all, we use the same"
Time stamp: 00:00-06:08

Direct transcription
"two modes, standard and extended thinking mode, which can be toggled in Amazon bedrock. In standard mode, Cloud 3.7 Sonic is an improved version of Cloud 3.5 Sonic. In extended thinking mode, claw 3.7 sonic takes additional time to analyze problems in detail, plan solutions, and consider multiple"
Time stamp: 00:00-06:08

Q summary
be toggled in Amazon bedrock. In standard mode, Cloud 3.7 Sonic is an improved version of Cloud 3.5 Sonic. In extended thinking mode, claw 3.7 sonic takes additional time to analyze problems in detail, plan solutions, and consider multiple perspectives before providing a response, allowing it
Time stamp: 03:58-04:22

Direct transcription
"In extended thinking mode, claw 3.7 sonic takes additional time to analyze problems in detail, plan solutions, and consider multiple perspectives before providing a response, allowing it to make further gains in performance. You can control speed and cost by choosing when to use reasoning"
Time stamp: 03:06-06:08

Q summary
its predecessor compared to claw 3.5 Soid, this model offers significantly expanded output length. This enhanced capacity is particularly useful when you explicitly request more detail, ask for multiple examples, or request additional context or background information. To achieve long outputs
Time stamp: 03:06-03:58

Direct transcription
"its predecessor compared to claw 3.5 Soid, this model offers significantly expanded output length. This enhanced capacity is particularly useful when you explicitly request more detail, ask for multiple examples, or request additional context or background information. To achieve long outputs"
Time stamp: 00:00-06:08

Direct transcription
"an industry leading 70.3% for standard mode on SWE bench verified. Claw 3.7 sonnet also performs better than Claw 3.5 sonnet across the majority of benchmarks. These enhanced capabilities make Cloud 3.7 sonnet ideal for powering AI agents and complex workflows.\[spk_0\]: Clawed 3.7 signed"
Time stamp: 06:08-07:52