
Anyone deploying capital leverage to legal AI right now will look like a genius. The more capital, the more genius. But the scores won’t be clear until someone falls over their skis.
Mitch
752 posts

@mitchellhynes
🇨🇦 Build Canada https://t.co/23LwJElfXJ https://t.co/4dTRjxIG8E @SpellbookLegal

Anyone deploying capital leverage to legal AI right now will look like a genius. The more capital, the more genius. But the scores won’t be clear until someone falls over their skis.




Cursor just one-shot a task that Claude, Codex and OpenCode failed at. AGAIN. Idk why I bother

We've raised $6.5M to kill vector databases. Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest. Similar, sure. Relevant? Almost never. Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough. A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file. Once you’re dealing with 10M+ documents, these mix-ups happen all the time. VectorDB accuracy goes to shit. We built @hydra_db for exactly this. HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time. So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit. Even when a vector DB's similarity score says 0.94. More below ⬇️



"make me a nidhogg clone" Codex is great!

There is no future in replit, loveable, v0, base44, bolt, or vibedev. It’s all just a larp of how much ARR can we lie about to raise more to repeat the same cycle. Nothing of value is ever created.

