Our team tested single- vs multi-agent setups using GPT-5, GPT-5-mini, and GPT-5-nano, using 10K+ tools across 30 domains. In the single-agent setup, GPT-5-mini and GPT-5-nano performance degrades with longer context and more reasoning, while GPT-5 remains remarkably consistent.
LLMS
-
OpenAPI Toolkit Upgrades: Convert Specs to LLM-Ready Tools
By
–
5/📜 OpenAPI Toolkit upgrades
— FlowiseAI (@FlowiseAI) 10 octobre 2025
This toolkit turns any OpenAPI (Swagger/JSON) spec into a set of LLM-ready tools – kinda similar to MCP!
Simply drop an OpenAPI spec link like: https://t.co/CI2AgIW0HD and watch the magic 🪄 pic.twitter.com/kLRUN2ieY25/📜 OpenAPI Toolkit upgrades This toolkit turns any OpenAPI (Swagger/JSON) spec into a set of LLM-ready tools – kinda similar to MCP! Simply drop an OpenAPI spec link like: api.apis.guru/v2/specs/groun… and watch the magic 🪄
→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
Built-in Web Search and Fetch Tools for Gemini and Anthropic
By
–
2/🌐 Built-in web search & fetch for Gemini + Anthropic
— FlowiseAI (@FlowiseAI) 10 octobre 2025
Combining these tools allow agent to:
1. Use web search to find relevant articles
2. Select the most promising results
3. Use web fetch to retrieve full content
4. Provide detailed response pic.twitter.com/NiosvYMVLO2/🌐 Built-in web search & fetch for Gemini + Anthropic Combining these tools allow agent to: 1. Use web search to find relevant articles 2. Select the most promising results 3. Use web fetch to retrieve full content 4. Provide detailed response
→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
Flowise Launches Text-to-Speech Feature with OpenAI and ElevenLabs
By
–
1/🔉 Text to Speech
— FlowiseAI (@FlowiseAI) 10 octobre 2025
Since launching Speech-to-Text, we’ve had tons of requests for the reverse: Text-to-Speech.
Now you have both STT and TTS!
Starting with OpenAI and @ElevenLabs voice models, welcome contributions to add even more variety!
Sound on: pic.twitter.com/9CQDmFi5Cd1/🔉 Text to Speech Since launching Speech-to-Text, we’ve had tons of requests for the reverse: Text-to-Speech. Now you have both STT and TTS! Starting with OpenAI and @ElevenLabs voice models, welcome contributions to add even more variety! Sound on:
→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
Flowise v3.0.8 Released with TTS and Web Search Features
By
–
What a week! 😮💨 We’re still shipping regardless, v3.0.8 is live! New in this release: 🔉 TTS (OpenAI + ElevenLabs) 🌐 Built-in web search & fetch for Gemini + Anthropic 🗄️ Teradata MCP 🖥️ Oxylabs scraper 📜 OpenAPI Toolkit upgrades Let's dive in 🏄
→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
Processing 1.3 Quadrillion Tokens Monthly Demonstrates Massive Scale
By
–
We processed over 1.3 Quadrillion tokens last month – that's 1,300,000,000,000,000 tokens! or to put it another way that's 500M tokens a second or 1.8 Trillion tokens an hour…
-
GPT-5 Pro Performance Issues Prompt Reversion to High Thinking
By
–
GPT-5 Pro is super slow, so we have reverted to GPT-5 High Thinking for now Also please check http://
livebench.ai – they are no different -
Benchmark Progress Achieved Despite Remaining Visual Artifacts
By
–
Big progress on this important benchmark (but still weird artifacts). https://t.co/1mz8SCJisk pic.twitter.com/f9tpCi9fne
— Ethan Mollick (@emollick) 10 octobre 2025Big progress on this important benchmark (but still weird artifacts).
-
Meta’s Stochastic Activation Achieves 90% Sparsity LLM Speedup
By
–
First ever activation function swapping strategy just dropped for LLMs! Meta’s new Stochastic Activation proposes a new method which randomly selects between non-linear functions (ReLU & SiLU) in the FFN of LLM, achieving an activation sparsity of 90% with 1.65x CPU speedups!
-
Automatic Language Detection and Title Generation for arXiv Articles
By
–
https://alphaxiv.org/pdf/2509.22358