Vividh

👀 where next?

Model companies became app companies. All app companies with data at scale will become model companies. It’s inevitable.

→ Search the web for live sports scores and stock prices → Find files on my desktop and run shell commands → Write code and solve math problems → Everything Claude Code does — for free The breakthroughs that made this possible: Apple's "LLM in a Flash" paper showed models can page from SSD using unified memory. I proved it works in practice on consumer hardware — not just in a research lab. Google's TurboQuant research showed you can compress KV cache with zero quality loss. I applied this with two server flags and doubled my context window from 32K to 64K tokens. For free. No code changes. The biggest surprise: the 35B model at 2.6 bits per weight was supposed to have "broken" tool calling. Every agent framework I tried failed — infinite loops, no answers. I stopped asking the model to generate JSON function calls. Instead I ask it simple questions. "Is this a search, shell, or chat?" → one word answer. Works perfectly. The tool calling wasn't broken. The protocol was wrong. Both models. Full agent. Same $600 computer: → 35B MoE: 30 tok/s, 2x faster, smarter reasoning → 9B dense: 16 tok/s, 64K context, reads entire codebases I benchmarked everything: → 212 math problems: 86.3% accuracy (3 categories at 100%) → 10 web search categories: 10/10 accurate → Shell commands: finds videos, checks disk space, reads code → MLX vs llama.cpp: tested both, llama.cpp wins for 35B

Does anyone actually get a degree from Waterloo or do they all drop out to make startups?