Treat your demos like blog posts. Post a ton, see what resonates, and double down.
@yoheinakajima
-
User Interaction Drives AI Self-Improvement and Data Generation
By
–
Thanks! Yeah I think building in user interaction can generate helpful data to continue self-building better and better.
-
Function Creation Complexity and Multi-Agent Consensus Approaches
By
–
I tried to keep this high-level but the “Create Function” step to get past level 1 is really complicated and there are tons of approaches/tricks here. Curious about your multi agent consensus.
-
Auto-installing imports without user consent raises safety concerns
By
–
That would be smart, but my current system goes as far as auto installing imports without user consent…. no user feedback is baked in
-
API Key Management and Automated Access Request System
By
–
1. In my current system I track which functions require what api keys (or secrets), which gets loaded into the environment. Since we know when an api key is required, we could set up a user request feature to ask for help, or give it an email,$, and multi-on access to grab an API
-
Building Reusable Functions for AI Agents
By
–
Good call. I didn’t include it here but my “Create function” step breaks the task down into multiple reusable functions, and then a wrapper function that uses those. So I think with good reasoning (plus external search when helpful), the agent should be building tools you don’t
-
AI Code Generation Framework Capabilities and Limitations
By
–
Oh it doesn’t yet. The code it generates sucks. But the framework does the heavy lifting.
-
Claude Sonnet 3.5 Outperforms GPT-3.5 in AI Model Comparison
By
–
gpt3.5, forgot I need to clarify. sonnet 3.5 rocks
-
Developer upgrading AI model framework using LiteLLM
By
–
I am weirdly using 3.5 as I work on the framework, and plan on upgrading the model once framework is solid as a fun surprise for myself (using LiteLLM so easy to swap)
-
Level 3 Self-Build Agent Prototype with Query Processing
By
–
Now it's far working well (as you can see from the errors…), but here's the output of a prototype self-build agent (lvl 3): – User description as input – Generate queries – Process query – Generates and stores multiple reusable functions for that query excited to share