akira_067

↗ HN profile [ 61.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Model naming has seemingly been an issue recently, especially with OpenAi, and so I wanted to take a moment to discuss this. Researchers consistently are, well, researchers. Their goal is to do research, not to name…

  2. I'm currently building coding agents, and wondering what the standard is for creating and running evals for most people? I gather that the tasks and their definitions will be dramatically different across domains and…

  3. https://x.com/0xrandomlabs/status/1991329720231948499?s=20 Ok so like the title says, agent frameworks suck, but they shouldn't right? What makes a good agent framework? Seems like some degree of expressiveness over the…

  4. Really curious about a couple things: What are people's current definitions for AGI and the appropriate timelines for them? How does the capability increase in something like coding bode for generalization in your eyes?…

  5. Gemini 3 is cool. Sure. Gemini 3 seems to be a strong model capable at everything you'd want. Long context, good ui design, good awareness of the codebase, and a strong ability to make decisions. What is strange to me…