home.social

#aitooling — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #aitooling, aggregated by home.social.

fetched live
  1. New tutorial on The Main Thread.

    An MCP tool call is analysis. Posting to the ledger is a separate step. This one builds a Quarkus MCP server for invoice reconciliation that uses elicitation for business policy, progress for batch visibility, and cooperative cancellation when someone picks the wrong supplier.

    - Two tools, one boundary: reconcile proposes, post commits.
    - 18 integration tests prove the separation.

    the-main-thread.com/p/mcp-invo

    #MCP #Quarkus #Java #AITooling #AccountsPayable

  2. New tutorial on The Main Thread.

    An MCP tool call is analysis. Posting to the ledger is a separate step. This one builds a Quarkus MCP server for invoice reconciliation that uses elicitation for business policy, progress for batch visibility, and cooperative cancellation when someone picks the wrong supplier.

    - Two tools, one boundary: reconcile proposes, post commits.
    - 18 integration tests prove the separation.

    the-main-thread.com/p/mcp-invo

    #MCP #Quarkus #Java #AITooling #AccountsPayable

  3. New tutorial on The Main Thread.

    An MCP tool call is analysis. Posting to the ledger is a separate step. This one builds a Quarkus MCP server for invoice reconciliation that uses elicitation for business policy, progress for batch visibility, and cooperative cancellation when someone picks the wrong supplier.

    - Two tools, one boundary: reconcile proposes, post commits.
    - 18 integration tests prove the separation.

    the-main-thread.com/p/mcp-invo

    #MCP #Quarkus #Java #AITooling #AccountsPayable

  4. New tutorial on The Main Thread.

    An MCP tool call is analysis. Posting to the ledger is a separate step. This one builds a Quarkus MCP server for invoice reconciliation that uses elicitation for business policy, progress for batch visibility, and cooperative cancellation when someone picks the wrong supplier.

    - Two tools, one boundary: reconcile proposes, post commits.
    - 18 integration tests prove the separation.

    the-main-thread.com/p/mcp-invo

    #MCP #Quarkus #Java #AITooling #AccountsPayable

  5. New tutorial on The Main Thread.

    An MCP tool call is analysis. Posting to the ledger is a separate step. This one builds a Quarkus MCP server for invoice reconciliation that uses elicitation for business policy, progress for batch visibility, and cooperative cancellation when someone picks the wrong supplier.

    - Two tools, one boundary: reconcile proposes, post commits.
    - 18 integration tests prove the separation.

    the-main-thread.com/p/mcp-invo

    #MCP #Quarkus #Java #AITooling #AccountsPayable

  6. “Kelley describes why he created Zig, when other options including C, C++, Rust, and Go already exist. He said he set out to develop a digital #audio workstation. He tried Go, but found interoperability with C libraries difficult, and said the garbage collector caused audio delays. He tried C++, or coding C-style using a C++ compiler, but found that small mistakes led to memory corruption bugs that took weeks to fix. He tried Rust but "really struggled to write code that would satisfy Rust's rules," and spent a month trying to make font rendering work”

    “The #Zig project is known for its #NoAI policy, set out in the code of conduct… Another negative for #AITooling is that it is #NonDeterministic and therefore its output always needs review, even for something as simple as refactoring the name of a function. Kelley prefers #deterministic tools in which he can have full confidence.“

    #Software / #Languages / #AndrewKelly <theregister.com/software/2026/>

  7. “Kelley describes why he created Zig, when other options including C, C++, Rust, and Go already exist. He said he set out to develop a digital #audio workstation. He tried Go, but found interoperability with C libraries difficult, and said the garbage collector caused audio delays. He tried C++, or coding C-style using a C++ compiler, but found that small mistakes led to memory corruption bugs that took weeks to fix. He tried Rust but "really struggled to write code that would satisfy Rust's rules," and spent a month trying to make font rendering work”

    “The #Zig project is known for its #NoAI policy, set out in the code of conduct… Another negative for #AITooling is that it is #NonDeterministic and therefore its output always needs review, even for something as simple as refactoring the name of a function. Kelley prefers #deterministic tools in which he can have full confidence.“

    #Software / #Languages / #AndrewKelly <theregister.com/software/2026/>

  8. “Kelley describes why he created Zig, when other options including C, C++, Rust, and Go already exist. He said he set out to develop a digital #audio workstation. He tried Go, but found interoperability with C libraries difficult, and said the garbage collector caused audio delays. He tried C++, or coding C-style using a C++ compiler, but found that small mistakes led to memory corruption bugs that took weeks to fix. He tried Rust but "really struggled to write code that would satisfy Rust's rules," and spent a month trying to make font rendering work”

    “The #Zig project is known for its #NoAI policy, set out in the code of conduct… Another negative for #AITooling is that it is #NonDeterministic and therefore its output always needs review, even for something as simple as refactoring the name of a function. Kelley prefers #deterministic tools in which he can have full confidence.“

    #Software / #Languages / #AndrewKelly <theregister.com/software/2026/>

  9. “Kelley describes why he created Zig, when other options including C, C++, Rust, and Go already exist. He said he set out to develop a digital #audio workstation. He tried Go, but found interoperability with C libraries difficult, and said the garbage collector caused audio delays. He tried C++, or coding C-style using a C++ compiler, but found that small mistakes led to memory corruption bugs that took weeks to fix. He tried Rust but "really struggled to write code that would satisfy Rust's rules," and spent a month trying to make font rendering work”

    “The #Zig project is known for its #NoAI policy, set out in the code of conduct… Another negative for #AITooling is that it is #NonDeterministic and therefore its output always needs review, even for something as simple as refactoring the name of a function. Kelley prefers #deterministic tools in which he can have full confidence.“

    #Software / #Languages / #AndrewKelly <theregister.com/software/2026/>

  10. “Kelley describes why he created Zig, when other options including C, C++, Rust, and Go already exist. He said he set out to develop a digital #audio workstation. He tried Go, but found interoperability with C libraries difficult, and said the garbage collector caused audio delays. He tried C++, or coding C-style using a C++ compiler, but found that small mistakes led to memory corruption bugs that took weeks to fix. He tried Rust but "really struggled to write code that would satisfy Rust's rules," and spent a month trying to make font rendering work”

    “The #Zig project is known for its #NoAI policy, set out in the code of conduct… Another negative for #AITooling is that it is #NonDeterministic and therefore its output always needs review, even for something as simple as refactoring the name of a function. Kelley prefers #deterministic tools in which he can have full confidence.“

    #Software / #Languages / #AndrewKelly <theregister.com/software/2026/>

  11. Top 7 MCP clients for AI tooling reviewed: Claude Desktop, Cursor AI, Claude Code, Windsurf, Cline, Continue & LibreChat. MCPs bridge AI models with real-world tools like databases & APIs. These clients make setup easy - often just adding a config line. kdnuggets.com/top-7-mcp-client

  12. Top 7 MCP clients for AI tooling reviewed: Claude Desktop, Cursor AI, Claude Code, Windsurf, Cline, Continue & LibreChat. MCPs bridge AI models with real-world tools like databases & APIs. These clients make setup easy - often just adding a config line. #AI #MachineLearning #MCP #AITooling #TechReview #Coding #Development #ArtificialIntelligence kdnuggets.com/top-7-mcp-client

  13. Top 7 MCP clients for AI tooling reviewed: Claude Desktop, Cursor AI, Claude Code, Windsurf, Cline, Continue & LibreChat. MCPs bridge AI models with real-world tools like databases & APIs. These clients make setup easy - often just adding a config line. #AI #MachineLearning #MCP #AITooling #TechReview #Coding #Development #ArtificialIntelligence kdnuggets.com/top-7-mcp-client