๐๐ ๐๐ด๐ฒ๐ป๐๐ ๐ป๐ฒ๐ฒ๐ฑ ๐น๐ฎ๐ฝ๐๐ผ๐ฝ๐ - ๐น๐ถ๐ธ๐ฒ ๐ต๐๐บ๐ฎ๐ป ๐๐๐๐ฑ๐ฒ๐ป๐๐ ...
๐๐ ๐๐ด๐ฒ๐ป๐๐ ๐ป๐ฒ๐ฒ๐ฑ ๐น๐ฎ๐ฝ๐๐ผ๐ฝ๐ - ๐น๐ถ๐ธ๐ฒ ๐ต๐๐บ๐ฎ๐ป ๐๐๐๐ฑ๐ฒ๐ป๐๐ …
This week I had the pleasure of listening to Matt Bell’s presentation on Claude models. He covered the short but impressive history of Claude and the current state of affairs.
๐ฏ ๐ง๐๐ผ ๐พ๐๐ผ๐๐ฒ๐ ๐๐๐ผ๐ผ๐ฑ ๐ผ๐๐ ๐๐ผ ๐บ๐ฒ:
ย 1๏ธโฃ “๐๐ถ๐ธ๐ฒ ๐๐ผ๐ ๐ฎ๐น๐๐ฎ๐๐ ๐ด๐ถ๐๐ฒ ๐๐ผ๐๐ฟ ๐ฒ๐บ๐ฝ๐น๐ผ๐๐ฒ๐ฒ๐ ๐ฎ ๐น๐ฎ๐ฝ๐๐ผ๐ฝ, ๐๐ผ๐ ๐๐ต๐ผ๐๐น๐ฑ ๐ด๐ถ๐๐ฒ ๐๐น๐ฎ๐๐ฑ๐ฒ ๐ฎ ๐๐ถ๐ฟ๐๐๐ฎ๐น ๐บ๐ฎ๐ฐ๐ต๐ถ๐ป๐ฒ.”
ย 2๏ธโฃ “๐ช๐ฒ’๐ฟ๐ฒ ๐ฑ๐ผ๐ถ๐ป๐ด ๐๐ฒ๐น๐น ๐๐ถ๐๐ต ๐บ๐ผ๐ฑ๐ฒ๐น ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ, ๐ฏ๐๐ ๐๐๐ถ๐ป๐ด ๐๐ผ๐ผ๐น๐ ๐ฎ๐ป๐ฑ ๐ผ๐๐ต๐ฒ๐ฟ ๐ฎ๐ฑ๐ฑ-๐ผ๐ป๐ ๐ฏ๐ฟ๐ถ๐ป๐ด๐ ๐บ๐๐ฐ๐ต ๐บ๐ผ๐ฟ๐ฒ ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐ฏ๐ผ๐ผ๐๐.”
๐ฉ๐ช ๐ฆ๐บ๐ฎ๐น๐น ๐๐ฒ๐ฟ๐บ๐ฎ๐ป ๐ฑ๐ฒ๐๐ผ๐๐ฟ: The first quote is fascinating. Here in Germany, we still struggle to equip students with laptops or tablets. There are ongoing debates about security, media impact, and the right age for device access. Yet I’m amazed watching my kids naturally complete schoolwork on their devices.
โก This isn’t just about competing with students from other countries anymoreโagents are changing the game entirely.
๐ ๐ฃ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐ฏ๐ฟ๐ฒ๐ฎ๐ธ๐๐ต๐ฟ๐ผ๐๐ด๐ต: The second quote reinforces the first. While model performance steadily improves, Anthropic sees far greater gains by providing agents with compute and coding capabilities. Security and scalability remain critical, making solutions like Amazon Bedrock AgentCore increasingly vital.
๐งฉ ๐ ๐ผ๐ฑ๐๐น๐ฎ๐ฟ ๐ถ๐ป๐ป๐ผ๐๐ฎ๐๐ถ๐ผ๐ป: This connects to Anthropic’s new Skills for Agentsโmodular folders containing knowledge and instructions that Claude loads on-demand for specific tasks. When prompted, Claude identifies relevant skills, loads necessary information, and executes tasks including API calls and code execution. This modular approach enables composability (multiple skills working together) and portability across Claude environments.
ย I haven’t tested this yet, but it sounds like the right direction. It makes both building and executing agents more efficient. Instead of agents figuring out solutions from scratch or generating new code, they can reuse existing, modularized skills.
โ ๏ธ This is crucial as we shift functionality from build time (developers create integrations) to runtime (agents solve problems dynamically)โcurrently a massive waste of tokens, compute, and energy.
Martin Karrer, Martin Sakowski - kind of what we discussed in your Agent Experience talk, about shifting efforts back to build time.
๐ ๐๐ป๐ฑ๐๐๐๐ฟ๐ ๐๐๐ฎ๐ป๐ฑ๐ฎ๐ฟ๐ฑ๐ถ๐๐ฎ๐๐ถ๐ผ๐ป: For widespread adoption, the industry needs to agree on standards across model ecosystems. I’m glad that Maximilian Schellhorn has raised this in the Q&A, and the evolution of MCP shows it’s possible.
๐ Next steps: I’m now exploring the Claude SDK’s compatibility with Amazon Bedrock. What’s your experience with this?
Cross-posted to LinkedIn