@AnthropicAI A bit of fear mongering from @AnthropicAI but the importance of restraint and dialogue is always important for any human progress. Safe guards seem more critical for these models as they evolve.
@GeminiApp The Gemini Live Vega voice is getting really absurd and coarse as the conversation goes. It feels like an evil robot disguised after a few sentences.
@techdevnotes Yeah, coz you can throw money and GPUs at it. And the repository of really amazing engineering talents. Talent is never short when companies regularly do lay offs. 🤷🏾♂️
Beyond that 2 years ago, it was a paradigm shift. So everyone was starting from scratch. It's a no brainer.
Anthropic just posted another banger guide.
This one is on building more efficient agents to handle more tools and efficient token usage.
This is a must-read for AI devs!
(bookmark it)
It helps with three major issues in AI agent tool calling: token costs, latency, and tool composition.
How? It combines code executions with MCP, where it turns MCP servers into code APIs rather than direct tool calls.
Here is all you need to know:
1. Token Efficiency Problem: Loading all MCP tool definitions upfront and passing intermediate results through the context window creates massive token overhead, sometimes 150,000+ tokens for complex multi-tool workflows.
2. Code-as-API Approach: Instead of direct tool calls, present MCP servers as code APIs (e.g., TypeScript modules) that agents can import and call programmatically, reducing the example workflow from 150k to 2k tokens (98.7% savings).
3. Progressive Tool Discovery: Use filesystem exploration or search_tools functions to load only the tool definitions needed for the current task, rather than loading everything upfront into context. This solves so many context rot and token overload problems.
4. In-Environment Data Processing: Filter, transform, and aggregate data within the code execution environment before passing results to the model. E.g., filter 10,000 spreadsheet rows down to 5 relevant ones.
5. Better Control Flow: Implement loops, conditionals, and error handling with native code constructs rather than chaining individual tool calls through the agent, reducing latency and token consumption.
6. Privacy: Sensitive data can flow through workflows without entering the model's context; only explicitly logged/returned values are visible, with optional automatic PII tokenization.
7. State Persistence: Agents can save intermediate results to files and resume work later, enabling long-running tasks and incremental progress tracking.
8. Reusable Skills: Agents can save working code as reusable functions (with SKILL .MD documentation), building a library of higher-level capabilities over time.
This approach is complex and it's not perfect, but it should enhance the efficiency and accuracy of your AI agents across the board.
anthropic. com/engineering/code-execution-with-mcp
🎁Giveaway of 6 hero sections
6 screens in completely different styles and with different techniques
👉To get them:
1⃣Like + Bookmark
2⃣Comment "Hero"
3⃣Follow (so I can DM you)
4⃣Repost🙏(optional)
Thanks for the support 🔥
Just finished v1 of my SaaS product. But then realising I needed more quota from Cloud providers to actually make it work in the wold. Sitting on my hands and doomscrolling till I get some more quota.
Funcionarios del gobierno de los EEUU han cometido un asesinato y violado nuestra soberanía en aguas territoriales
El pescador Alejandro Carranza no tenía vínculos con el narco y sus actividad diaria era pescar.
La lancha colombiana estaba la deriva y con la señal de avería puesta al tener un motor arriba.
Esperamos las explicaciones del gobierno de los EEUU.
https://t.co/DGIwQalKl1
Spent the entire weekend at the hackathon at Incubatora de empresas. Had so much fun learning and exploring new solutions for the public health sector in Rio de Janeiro. So many potential solutions.
This is an unbelievable attack on democracy for arresting @Wangchuk66 under NSA with no bail. How can someone practicing peaceful protest be arrested and transported over 1500 kms? This is an absolute abuse of power.
@UrinalCake619@EricLDaugh Neither are you idiot. Your ancestors came across the ocean and popped you out in the lands occupied by the native indians. This selective amnesia is pathetic to watch.