In 30 Sekunden
Matthew Berman demonstrates Anthropic’s newly introduced web search in Claude, turning it on and asking about the latest video on his channel. He shows the search queries and sources and suggests finding current programming documentation as a potential use. The short does not show a verified final answer.
- 1Enable web searchClaude presents a prompt and a toggle for enabling web search in the demonstrated interface.
- 2Model selectionBerman says the feature can be used with Claude 3.7 Sonnet and extended thinking.
- 3A query about a YouTube channelClaude searches several sources and refines the query; the clip does not show a confirmed result.
- 4A suggested coding useBerman suggests searching for updated library documentation as a potential application.
Das Wichtigste
- Berman enables web search using the prompt in Claude’s interface.
- He says the feature can be used with Claude 3.7 Sonnet and extended thinking in his 2025 demonstration.
- The example shows several search attempts but does not establish that the final answer is correct.
- Searching current library documentation is a suggested use, not a task tested in the clip.
Den bearbeiteten Text nach Kapiteln lesen
Enabling and testing web search
Berman turns on Claude’s web search and describes the model options shown in March 2025. He asks about his latest YouTube video.
Anthropic has added web search to Claude, a feature I have wanted for a long time. When I open Claude, the interface prompts me to enable it, and a toggle lets me turn it on. In this March 2025 demonstration, I say the feature works with the available models, including Claude 3.7 Sonnet with extended thinking.
I ask Claude for the latest video published on my YouTube channel. It searches sources including LinkedIn, vidIQ and ThoughtLeaders, then refines the search several times. The clip shows the searches rather than a verified final answer. One potential use I suggest is finding current documentation for programming libraries.
Search results and potential uses
The interface shows sources and further searches. Berman suggests up-to-date coding documentation as another use, without testing it here.
Mehr aus diesem Kanal
34:21EN
Matthew Berman· 27. Okt. 2026Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.
0:26ENMatthew Berman· 25. Okt. 2026Sam Altman on Human Values and Problem-Solving in an AI WorldSam Altman · OpenAIIn a short interview excerpt, Altman considers the enjoyment of solving hard problems and the human role in interpreting results.
0:36ENMatthew Berman· 25. Okt. 2026Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.
0:21ENMatthew Berman· 24. Okt. 2026An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.
25:50ENMatthew Berman· 24. Okt. 2026Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.
32:20ENMatthew Berman· 23. Okt. 2026Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.