what's up with this graph, the box heights are all over, did chatgpt agent generate it?
@jiquanngiam
-
Connecting MCPs to GPTs with Custom Actions Guide
By
–
Connecting MCPs to GPTs with custom actions is much harder than it needs to be, we wrote up a guide here for it:
-
UI Design Critical for Long-Running Agent Tool Calls
By
–
Huge, we build a lot of agents and realize that making really nice UI for tool calls (esp. long running ones) were critical for a good user experience.
-
Cost Plus Pricing Model for AI Usage and Services
By
–
Cost plus model! We use a similar model for usage. Interested to learn more
-
MCPs ChatGPT Integration: Limitations and Developer Capabilities
By
–
The state of MCPs with ChatGPT is confusing, here's what we found: As an end-user, you can connect MCPs to ChatGPT connectors, but those MCPs must only two tools: `search` and `fetch`. Also, they only work in deep research or agent mode. As a developer, you can use MCP with
-
Agents Are the Future: Composio Innovation Highlighted
By
–
Agents are the future! Nice work @composio @KaranVaidya6
-
Tools Transform AI Agents Into Effective Coworkers
By
–
The big unlock is tools. Give an agent the right tools, and it stops being a chatbot, it becomes a coworker.
-
Building AI Agents That Understand Personal Computing Needs
By
–
Great podcast episode on how we're building with AI and agents that get things done. Our computers are getting more personal than ever with AI, they can now understand our needs, specific apps we use, and are able to get things done. Really enjoyed our conversation, thanks for
-
LLM Architecture: Separating Data from Logic
By
–
Actually, no. We have an architecture that separates data and logic. The LLM often never sees the data at all. Read more:
-
LLM Objectivity Issues: Reinforcing Beliefs Over Critical Thinking
By
–
Finding myself wishing that LLMs were giving me more objective thoughts, rather than trying to reinforce my beliefs. Every turn I ask Claude to “revisit your assumptions”, it flips back and forth. Almost like it treats the message as an instruction to flip its view.