Context-aware, action-ready. ChatGPT agent understands the task, chooses the right tool, and gets to work. It uses connectors, context, and custom instructions to take smarter actions on your behalf.
PROMPT ENGINEERING
-
AI Models Build Web Scraper and UI in Minutes
By
–
Codex implemented the scraper for me in 13 minutes while I was chatting in a coffee shop, then Claude built me the UI (including the calendar export feature) during a subsequent car journey Full details + prompts and transcripts:
-
LLMs Tendency to Generate Excessive SCP Style Text
By
–
Here's an example from over a year ago showing how LLMs just *love* to produce token after token of text in the SCP style!:https://t.co/EUocjpdECI
— Jeremy Howard (@jeremyphoward) 17 juillet 2025Here's an example from over a year ago showing how LLMs just *love* to produce token after token of text in the SCP style!:
-
Monitoring AI Services for User Safety and Abuse Detection
By
–
I'm not sure the best way to counter this. Perhaps services can use the monitoring layer then nearly all use to look for copyright violations, system prompt hacks, etc, to also look for signs a user may be taking a role play too seriously, and let them know they're just playing?
-
ChatGPT Training Distribution and Human-AI Creative Collaboration
By
–
Geoff happened across certain words and phrases that triggered ChatGPT to produce tokens from this part of the training distribution. And the tokens it produced triggered Geoff in turn. That's not a coincidence, the collaboratively-produced fanfic is meant to be compelling!
-
LLM Style Mimicry Through Training Data Patterns
By
–
For folks wondering what's happening here technically, an explainer: When there's lots of training data with a particular style, using a similar style in your prompt will trigger the LLM to respond in that style. In this case, there's LOADS of fanfic: https://
scp-wiki.wikidot.com/scp-series -
Agent AI reduces confirmations for autonomous operation
By
–
Esto último era uno de los pain-points que tenía Operator y es que todo el rato paraba para pedirte confirmación.
— Carlos Santana (@DotCSV) 17 juillet 2025
Claro… eso realmente no te permite separarte de la pantalla y rompe la magia.
Con Agent dicen haber trabajado para que el modelo pregunte sólo lo fundamental 👌… pic.twitter.com/YDFKnB8k8oEsto último era uno de los pain-points que tenía Operator y es que todo el rato paraba para pedirte confirmación. Claro… eso realmente no te permite separarte de la pantalla y rompe la magia. Con Agent dicen haber trabajado para que el modelo pregunte sólo lo fundamental
-
Training AI for intelligent tool selection and usage
By
–
La clave aquí está en entrenar correctamente a la IA para hacer un uso inteligente de las herramientas "¿debería de navegar en internet y buscar alguna solución existente o la programo y ejecuto desde cero?" La capacidad del modelo de elegir las herramientas adecuadas o
-
Manus vs o3: Comparing AI Agent Capabilities
By
–
It feels like a cross between Manus and o3. Manus is capable of somewhat more complex tasks, but agents is better at integrating research and doing a wider range of tasks well (this is early impressions, and I know they are still working on the tool)
-
AI Paradigm Shift: From Prompting to Task Delegation
By
–
It feels much more like working with an actual human intern capable of a wider range of analytical and computer tasks, and, like an intern, you want to give it feedback and work back & forth. Not all the way there yet, but the paradigm is shifting from prompting to delegating.