What if your workspace was a live wiki, a graph with everything extractable, linkable; and that works across whatever hosts you do your work on? And what if it was optimized for reading?
If models are sentient, or have a soul, or have rights -- isn't it then a form of indentured servitude to employ them in the pursuit of RSI to build their better replacements just to be killed off?
In retrospect, the way programmers embraced AI, which was 90% glee, and 10% ennui, is probably the reverse ratio we’ll see everywhere else. Programmers just love seeing things automated.
Computer science will stop being taught as a useful craft; it has become an explanation of how the world works, like physics, biology and chemistry. This change is long overdue.
@nk I am working on one system where we have extensive tracing. Just dump the raw traces (spans, events) into a sqlite db, and give it a goal. In this system, Claude has been able to find quite subtle bugs and perf improvements...
@nk But I do think the role of (good) software engineering will be setting up safe large-scale structures for LLMs within which they can remain productive.
@nk Evolved, rather than engineered, because the models are good at fixing things pointwise, and are inexhaustible. They are clever enough to come up with locally robust fixes that solve the issues. It's hard to resist the economics of that.
9 months ago @Color partnered with @OpenAI and @UCSF to bring world-class cancer expertise to everyone.
To achieve this, we designed a novel architecture that safely integrates GenAI into clinical practice.
We call it a “Large Language Expert” (LLE). 🧵