Hacker News new | past | comments | ask | show | jobs | submit | from login
I use these MCP Servers every day (composio.dev)
1 point by lordfuckleroy 4 days ago | past | discuss
Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison (composio.dev)
483 points by mraniki 35 days ago | past | 328 comments
Notes on Gemini 2.5 Pro: The new coding SOTA (composio.dev)
1 point by sunilkumardash9 38 days ago | past | 1 comment
Composio.dev (composio.dev)
1 point by AnhTho_FR 56 days ago | past
Notes on the New Deepseek R1 (composio.dev)
6 points by soham123 3 months ago | past
Notes on the New Deepseek v3 (composio.dev)
99 points by soham123 4 months ago | past | 24 comments
Gemini 2.0 vs. OpenAI o1 vs. Claude 3.5 Sonnet: The game of AI thrones (composio.dev)
2 points by sunilkumardash9 4 months ago | past
OpenAI O1 vs. Claude 3.5 Sonnet: Which One's Worth Your $20? (composio.dev)
2 points by sunilkumardash9 4 months ago | past
AgentAuth: Seamless Authentication for AI Agents with 250 Tools (composio.dev)
1 point by rgarcia 5 months ago | past
Tool design is all you need for building SOTA coding agents (composio.dev)
4 points by sunilkumardash9 6 months ago | past
Notes on Anthropic's Computer Use Ability (composio.dev)
82 points by todsacerdoti 6 months ago | past | 103 comments
O1-preview Analysis, Great at math, reasoning, average at coding, writing? (composio.dev)
1 point by laziesthuman 7 months ago | past
GPT-4o function calling is 3x faster, 50% cheaper (composio.dev)
2 points by soham123 11 months ago | past
Opus is worse than Haiku and sonnet in terms for functional calling (composio.dev)
2 points by hudixt 11 months ago | past
Improving Function-Call Accuracy from 35% to 75% for GPT4 (composio.dev)
2 points by soham123 12 months ago | past
Improving GPT 4 Function Calling Accuracy (composio.dev)
40 points by hudixt 12 months ago | past | 1 comment

Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: