It's just a smart model that's good at stuff. o3 writes a little too short and uses tables too much. The other reasoning models are heavily optimized for code. But o1 Pro will do stuff like deep research + write you a personalized playbook to help you execute a specific task.
PROMPT ENGINEERING
-
Negative Reinforcement Improves LLM Reasoning Without Explicit Rewards
By
–
The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning This paper shows that punishing incorrect answers—without explicitly rewarding correct ones—can be surprisingly effective for improving reasoning in large language models trained via reinforcement learning
-
Chain-of-Thought Prompting: Constraint Mimicry Over True Reasoning
By
–
CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective This paper challenges the idea that Chain-of-Thought (CoT) prompting enables true reasoning in LLMs, arguing instead that CoT acts as a structural constraint that guides models to imitate
-
Input Token Proportionality in Language Model Economics
By
–
no…. they are both proportional to the number of input tokens…
-
Gemini 2.5 Pro Solves Hanoi Tower Problem with Limitations
By
–
Al final me he puesto a replicar también los resultados con los prompts del paper y me he hecho un validador del jueguito de las torres de hanoi.
— Carlos Santana (@DotCSV) 9 juin 2025
Gemini 2.5 Pro con 9 discos lo resuelve sin problema y con 10 ha fallado el primer intento. Pero en ambos casos no abortan la tarea. pic.twitter.com/qvZfdpQ4NpAl final me he puesto a replicar también los resultados con los prompts del paper y me he hecho un validador del jueguito de las torres de hanoi. Gemini 2.5 Pro con 9 discos lo resuelve sin problema y con 10 ha fallado el primer intento. Pero en ambos casos no abortan la tarea.
-
Vibe Coding Leveled Up: Full Apps with Single Prompt
By
–
Vibe coding leveled up. With a single prompt, you can create a full app with: •Rich visuals & content
•10–15 charts for trends
•Embedded AI chatbots
•Clean layouts
•Hosting, DB & login support -
AI Generates Complete Solar System Educational App via Vibe Coding
By
–
J’ai demandé à une IA de créer une app éducative complète sur le système solaire. En quelques prompts, elle a généré les fichiers, écrit le code, lancé le serveur.
— VISION IA (@vision_ia) 9 juin 2025
Pas besoin de connaître le CSS. C’est ça, le Vibe Coding.
⤵️ pic.twitter.com/u6U1QlymlfJ’ai demandé à une IA de créer une app éducative complète sur le système solaire. En quelques prompts, elle a généré les fichiers, écrit le code, lancé le serveur. Pas besoin de connaître le CSS. C’est ça, le Vibe Coding.
-
Typical Day in Los Angeles 2025, GTA Graphics Style
By
–
Google Veo 3 prompt:
— AI Breakfast (@AiBreakfast) 9 juin 2025
"Typical day in Los Angeles 2025, GTA graphics" pic.twitter.com/B9Fd352Aa0Google Veo 3 prompt: "Typical day in Los Angeles 2025, GTA graphics"
-
Model Efficiency vs Extended Thinking Budget Trade-offs
By
–
yeah default the model tries to be as efficient and correct as possible, it will stop if it thinks it has the right answer, vs max thinking budget will keep thinking and sometimes gets better results (though you will also see cases where it had the right answer but changed its