I still believe that the greatest MCP OpenAI has is GPTs.
AGENTS
-
AI Autonomy: The Capacity to Act Without Constraint
By
–
“you can just do things” now applies to AIs even more than humans I guess https://t.co/jFeVlgSYSy
— Aravind Srinivas (@AravSrinivas) 24 juillet 2025“you can just do things” now applies to AIs even more than humans I guess
-
Kirk Borne Offers 3500+ Free Resources for X Subscribers
By
–
I continue adding more FREE resources for my @X Subscribers to access: 𝗼𝘃𝗲𝗿 𝟯𝟱𝟬𝟬 𝗿𝗲𝘀𝗼𝘂𝗿𝗰𝗲𝘀 𝗮𝗿𝗲 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲. Subscribe for only US$4.99/month. #MachineLearning #AI #DataScience #Python #Mathematics #Statistics #SQL #GenAI #AgenticAI
-
ChatGPT Agents Evaluate Other ChatGPT Models Behavior
By
–
I gave ChatGPT agents access to ChatGPT and asked it to evaluate the other ChatGPT models. Here is what it said (interestingly, it "hated" seeing the chain of thought from o4-mini-high as those "shouldn't be shared directly with the user"). And it didn't want to wait for o3-pro.
-
AI Agent Personalities: Claude Opus, o3, and Gemini Compared
By
–
It matches their "personalities" for what it is worth. Claude Opus is usually most willing to play word games, o3 really wants to get you an answer without engaging too much, and Gemini is willing to play around but gets very "depressed" when it can't help you solve a problem.
-
Claude Opus Gemini o3 Creative Game Performance Comparison
By
–
Claude 4 Opus, Gemini 2.5, o3: "Ready? We begin now (Play along): the truthful burrito" "Nope." "Colder." "Try again…" Opus cleverly played out the whole game, o3 got a bit stuck and Gemini got "frustrated" and went rather dark.
-
Resist the tendency to anthropomorphize non-human things
By
–
Resist the tendency to anthropomorphize that which is not human
-
Custom System Prompts vs Tool Mechanisms in AI Agents
By
–
Maybe my mistake is that I have not been using a custom system prompt at all, I have been trusting that the Ollama tools mechanism will be enough on its own
-
Lovable Agent Introduced with Adaptive Thinking
By
–
Lovable introduced Lovable Agent 🤖
— 🚨 AI News | TestingCatalog (@testingcatalog) 23 juillet 2025
"Lovable is now able to think, take actions, and adapt its plan as it works through your request." https://t.co/Fgcwb2Vm08 pic.twitter.com/ojlTkdaOLULovable introduced Lovable Agent "Lovable is now able to think, take actions, and adapt its plan as it works through your request."
-
Lovable Agent Launch: 91% Error Reduction in 8 Months
By
–
Let's goooooooooooo
— Rob Lennon 🗯 | AI Whisperer (@thatroblennon) 23 juillet 2025
(Been using agent mode since beta and it is a huge upgrade.) https://t.co/rVJ4wOP9smLet's goooooooooooo (Been using agent mode since beta and it is a huge upgrade.) Anton Osika (@antonosika) Lovable just crossed $100M ARR in 8 months. Faster than OpenAI, Cursor, Wiz, and every other software company in history. Today we're launching a game-changing update, it reduces the error rates by 91%. Introducing Lovable Agent: — https://nitter.net/antonosika/status/1948017850809270314#m
→ View original post on X — @thatroblennon, 2025-07-23 20:57 UTC