#FunctionCalling
LightNews LightNews
kunalganglani.bsky.social
Updated: MCP vs OpenAI Function Calling: Lock-In vs Flexibility

MCP wins for multi-model, cross-vendor agent ecosystems; OpenAI function…

#MCP #FunctionCalling
https://www.kunalganglani.com/blog/mcp-vs-function-calling?utm_source=bluesky&utm_medium=update&utm_campaign=mcp-vs-function-calling
MCP vs OpenAI Function Calling: Lock-In vs Flexibility
MCP wins for multi-model, cross-vendor agent ecosystems; OpenAI function calling wins for teams already deep in the OpenAI stack. Your choice depends on how vendor-locked you're willing to be.
www.kunalganglani.com
November 9, 2026 at 6:04 AM
qiita-trending.bot.chrs.to
LLMはなぜ外部ツールを呼び出せる？Function Callingの内部動作とエージェント設計

#LLM #Functioncalling #OpenAI #LangChain #Agent
LLMはなぜ外部ツールを呼び出せる？Function Callingの内部動作とエージェント設計 - Qiita
多くのエンジニアが「LLMはただのテキスト生成器」と誤解していますが、実はGPTモデルは外部ツールを呼び出し、まるで人間のようにタスクを遂行できます。この強力な機能が「Function Calling」です。しかし、その内部でLLMがどのようにしてツールを呼び出すべきかを判...
qiita.com
September 27, 2026 at 2:20 PM
sergiocuellar.bsky.social
Function calling lets your code decide what runs based on model output, enhancing AI capabilities without direct execution. #FunctionCalling #AI #MachineLearning
AI Function Calling Explained With Real Python Code Examples
A language model cannot check your disk usage or query your database on its own. Function calling is the mechanism that changes that, and it takes about forty lines of Python to build.
kodekloud.com
September 26, 2026 at 6:39 AM
donwebmedia.bsky.social
El bug de Ollama que hace que gemma4 invente datos

¿Por qué Ollama inventa valores en tool calling? El ollama function calling bug en gemma4 borra type y description sin avisar. Mirá el fix de 12 líneas

#ollama #gemma4 #functioncalling #toolcalling #bugsdeia
El bug de Ollama que hace que gemma4 invente datos
Un parámetro llamado type o description desaparece del prompt en Ollama y el modelo rellena el hueco inventando. Causa técnica y fix explicados.
blog.donweb.com
September 16, 2026 at 3:16 AM
aidailypost.com
Google’s new ToolGrad framework is crushing it—99.8% pass on tool-use tasks, from API calls to Gemma-3 fine-tuning. Curious how they trained it? Dive into the data and see the next leap in function calling. #ToolGrad #ToolUse #FunctionCalling

🔗 aidailypost.com/news/googles...
September 11, 2026 at 6:15 AM
donwebmedia.bsky.social
Control plane asistente IA: mas alla de la API

Tu asistente de codigo se rompe en produccion? El control plane asistente IA resuelve contexto, memoria y failover en 3 capas. Como armarlo bien

#controlplane #asistentedecodigoia #functioncalling #failoveria #memoriavectorial
Control plane asistente IA: mas alla de la API
Ruteo de herramientas, memoria persistente y failover automatico: las 3 capas que separan un asistente de codigo de demo de uno de produccion.
blog.donweb.com
August 27, 2026 at 8:31 AM
kindtech.bsky.social
Function calling is probabilistic by nature, so treat tool invocations like user input. Validate every argument at the boundary, retry on schema errors, never let the model guess missing parameters. The tools work, the glue code is where pipelines die. #FunctionCalling #AIAgents #Tooling
August 20, 2026 at 10:50 AM
latitude77.bsky.social
Advanced Guide - Ollama Function Calling with Python | Toolworks.dev #dev #ollama #functioncalling #python
January 13, 2025 at 7:06 AM
bastacon.bsky.social
🚨 MCP kann zur Falle werden

@gregorbiswanger.bsky.social zeigt auf der #bastacon:
🔐 Security-Risiken
💸 Kostenfallen
⚙️ Function Calling

📅 Donnerstag, 01. Oktober 2026 | 🕘 10:30 - 11:30 | BASTA! | 📍 Mainz

🔗 https://tinyurl.com/64shcj7a

#AI #MCP #Security #GenAI #FunctionCalling
June 24, 2026 at 9:02 AM
dorialexander.bsky.social
Well, it got delayed but SYNTH functioncalling was the next release planned.
February 17, 2026 at 8:06 PM
mengli512.bsky.social
Explore OpenAI’s revamped Function Calling Guide! 50% shorter docs, best practices, clear workflows, and intuitive design for developers.

#AI #OpenAI #FunctionCalling #LLM #Agent
aidisruption.ai/2025/01/15/o...
OpenAI Updates Function Calling Guide with “Least Astonishment” Principle
OpenAI Function Calling Updates! This time, the big change: document length cut in half, yet introducing clearer “software engineering best practices”! It’s not just a simple document update — it’s…
aidisruption.ai
January 14, 2025 at 9:37 PM
sugatoray.bsky.social
@ollama.bsky.social Python library introduced #FunctionCalling in version 0.4.

Ollama is an AI tool that allows you to run Large Language Models (LLMs) on device (local LLM).

Ollama blog: ollama.com/blog/functio...

#ollama #python #LLMs #ml #ai #localLLM #localai
December 3, 2024 at 2:05 PM
hiroaki2.bsky.social
こんにちは、人工知能の勉強をしてるのですが、Ipaasと、function callingがどうしてもわかりません、よろしければ教えてください🙏
※私は数字とプログラミング全然わからないド素人です。

​#AI学習 #iPaaS #FunctionCalling
#非エンジニア #DX
February 4, 2026 at 7:25 AM
rabauer.dev
🎬 Full episode here: youtube.com/live/fww6351...
#Java #SpringAI #Ollama #LLM #FunctionCalling #AIgameDev #Vaadin #LiveCoding #AIintegration #DevThread
July 21, 2025 at 9:50 AM
donwebmedia.bsky.social
Patente Mistral tool calls: sandbox, pausas y delegación

¿Mistral acaba de reinventar las tool calls? La patente US12670045 propone ejecutar herramientas en sandbox con pausas y delegación al cliente. ¿Qué cam...

#mistral #toolcalls #patente #llm #functioncalling
Patente Mistral tool calls: así funciona el nuevo
¿Mistral acaba de reinventar las tool calls? La patente US12670045 propone ejecutar herramientas en sandbox con pausas y delegación al cliente. ¿Qué cam...
blog.donweb.com
August 10, 2026 at 3:14 PM
donwebmedia.bsky.social
Los 3 bucles que forman un agente de IA (y por qué importan)

¿Cómo funciona un agente de IA por dentro? Son 3 bucles apilados fingiendo ser uno. Descubrí cuál te salva de un desastre irreversible en producción

#agentesia #theagenticloop #functioncalling #llm #loopengineering
Bucles en agentes de IA: los 3 loops explicados
¿Cómo funciona un agente de IA por dentro? Son 3 bucles apilados fingiendo ser uno. Descubrí cuál te salva de un desastre irreversible en producción
blog.donweb.com
July 15, 2026 at 5:24 AM
donwebmedia.bsky.social
Tool Calls en Claude: el costo que no ves venir

Cuánto cuestan realmente las tool calls en Claude API en 2026, qué es Tool Search, cómo Programmatic Tool Calling ahorra 37% de tokens y por qué explota...

#claudeapi #tooluse #functioncalling #anthropic #agentesia
Costos herramientas Claude API: tool use real
Cuánto cuestan realmente las tool calls en Claude API en 2026, qué es Tool Search, cómo Programmatic Tool Calling ahorra 37% de tokens y por qué explota...
blog.donweb.com
May 4, 2026 at 4:42 PM
shun91.bsky.social
"FunctionCalling:各AIモデル（OpenAI、Anthropicなど）の仕様に依存し、インターフェイスがモデルごとに異なる。
MCP：MCPサーバーとMCPクライアント間の共通プロトコルに基づいており、特定のAIモデルに依存しません。"

https://zenn.dev/yamada_quantum/articles/465c4993465053
March 15, 2025 at 2:03 PM
wagesj45.mastodon.jordanwages.com.ap.brid.gy
Just implemented the first half of #ai #functioncalling in #homeassistant. Slow as shit, but it worked! 😃

#llm #qwen #qwen3
A screenshot of a debug output in Node-RED labeled "node: debug 2", timestamped 5/26/2025 at 2:41:02 AM. The output is an object containing a _msgid with value "8fef24a60334a3c7" and a payload of type string, which includes a JSON structure: { "tool": "call_service", "args": { "domain": "switch", "service": "toggle", "entity_id": "switch.office_light_switch" }, "repeat": false } Other fields include topic set to an empty string, user_prompt with the text: "Please turn on the office light.", and a collapsed light array of 13 elements.
May 26, 2025 at 7:48 AM
llms.activitypub.awakari.com.ap.brid.gy
AzureOpenAI入門：FunctionCallingで生成AI×ツールを実現する サイオステクノロジーのひろです。今回はAzureOpenAIを使用したFunctionCallingについて解説して...

#Azure #クラウド #生成AI #Azure #OpenAI #Function #Calling

Origin | Interest | Match
AzureOpenAI入門：FunctionCallingで生成AI×ツールを実現する | SIOS Tech Lab
サイオステクノロジーのひろです。今回はAzureOpenAIを使用したFunctionCallingについて解説していきます。 このブログのゴール ・FunctionCallingとは何かわかる ・AzureOpenAIモデルを使用したFunctionCallingの実装方法がわかる
tech-lab.sios.jp
February 25, 2026 at 8:31 AM
getnews-me.bsky.social
Guided templates raise LLM function-calling accuracy by 3%‑12% over strong baselines, improving reliability and interpretability across model sizes. Read more: https://getnews.me/guided-structured-templates-boost-llm-function-calling-accuracy/ #functioncalling #llm
Guided Structured Templates Boost LLM Function Calling Accuracy
September 25, 2025 at 6:45 AM
getnews-me.bsky.social
Research finds function calling lifts LLM safety, delivering a 135% gain in detecting unsafe content; the paper was submitted in September 2025. Read more: https://getnews.me/causality-based-study-reveals-how-function-calling-boosts-llm-safety/ #functioncalling #llmsafety
Causality-Based Study Reveals How Function Calling Boosts LLM Safety
September 24, 2025 at 4:31 AM
getnews-me.bsky.social
DyMo predicts environment changes after tool calls, raising success rates and cutting hallucinations. It outperformed baselines on the Berkeley Function Calling Leaderboard V2. https://getnews.me/dynamics-modelling-enhances-tool-use-for-language-model-agents/ #dymo #functioncalling
Dynamics Modelling Enhances Tool Use for Language Model Agents
September 22, 2025 at 11:57 PM
getnews-me.bsky.social
AgentScaler builds a framework that generates simulated environments and applies two‑phase fine‑tuning, boosting function‑calling performance on benchmarks tau‑bench, tau2‑Bench and ACEBench. Read more: https://getnews.me/agentscaler-boosts-general-agentic-intelligence/ #agentscaler #functioncalling
AgentScaler Boosts General Agentic Intelligence
September 18, 2025 at 6:19 PM
getnews-me.bsky.social
Voicing AI says its models reach over 97% function‑calling accuracy, far above the usual 80‑82% range, and offers a 70 B Enterprise Powerhouse model for complex tasks. Read more: https://getnews.me/voicing-ai-achieves-97-accuracy-in-enterprise-function-calling/ #voicingai #functioncalling
Voicing AI Achieves 97% Accuracy in Enterprise Function Calling
September 16, 2025 at 6:26 AM