I'm curious that giving an counter-example is kind of easy to disprove. But can the model really prove something correctly and rigorously? Cuz now it seems like all the knowledge is based on the existed thing, and none of them can prove a myth.
I was wondering that will modifying prompts or contracting the context also impact the performance? It may mistake the original meaning, and these steps also need help from external LLM.
Asking for a hundred billion in damages and having your multi-million dollar legal team defeated not on the merits of the case, but because they literally forgot to look at the calendar lol
kudos to the Martin-Baker seats and the pilots' training, ejecting at that low altitude after a collision is incredibly hazardous. Using high-value electronic warfare assets for aerobatics seems like an unnecessary risk when regular Hornets could do the exact same job for the crowd.
I'm working on a local-first AI app that combines a chatbot interface with agentic capabilities (similar to a GPT + OpenClaw mashup). Would love to hear what features you'd want in a "Local AI Copilot"!
Not making sense to me at all. The AI era should be a great opportunity for Github to show their reliability and developer-first law, but they decided to all in AI. As a developer, what I need is a well-working repository, not a agent that write, review, even publish the code for me.
How sad that I spent thousand dollars to buy the phone but can't own it at all. Hardware attestation is like having a CCTV in my device, reporting everything to the company. If I want to use safer OS, then I will be excluded by the digital society cuz most app don't support it...
The interactive challenges and the step-by-step mental models for recursive types and distributive conditionals are incredibly well-structured. It's cool to transform type gymnastics into a systematic engineering discipline.