That describes how hands off MS was with Postgres committers ime a few years ago. Useful to house them to for helpful office hours too. We'll see how that holds up post HorizonDB
LLMs are great for being nerdsniped. I started work on walshadow (reading pg wal into clickhouse) to demonstrate the project's infeasibility, but pieces started coming together into something reasonable & order of magnitude faster
The project would've been impossible for me without LLMs. & even with them there's an argument that this project is pushing complexity limits too far. But at least with ETL there's a clear feedback loop to build on
LLMs have introduced me to things like photodiodes and specific economists I would likely not have found on my own
I do however wonder about specific research priority/project from labs' solving their own problems leaking into my chats. I noticed one month that Claude really started harping on about "legibility" and suggesting Seeing Like A State to me, and saw it like any other interesting suggestion/insight.
Now I see a lot of people mentioning "legibility" and think that was just some weird attractor state or useful vocabulary term for being an LLM (that literally can't see certain things or be observed easily!). It's a weird feeling, because nobody tried to trick me and in fact it objectively helped me to acquire useful information. I just have to wonder if other people are having the same conversation and there's really nothing special about it - maybe Anthropic just really liked that book right around when they were doing a lot of RL
Not only that, was the intent just to give Claude the vocabulary to be an LLM in a company that wants it to be legible, and apply that book to managing it, and we're either intentionally or unintentionally memetically downstream of that? Or was it just extra likely to be mentioned because it's a genuinely helpful book - either because the AI learned over time that it was (very good!), someone just wanted to recommend it to more people to help them (~good). I worry that the "intelligent conversation" or "wow look at the agent go" can give us very poor epistemics
Thank you for introducing me to the word "nerd-sniping"[1].
This is, as you say, exactly the paradox of having ourselves assisted by LLMs. We are no different from our cats. Except imagine the cats start making the laser lights for themselves.
model produces lower quality code when *the dataset it's trained on has been operating under the break fast and move things MBA-brained mentality for decades
With pg_clickhouse this doubled throughput while reducing memory usage. The original motivation was to supplant clickhouse-cpp to remove C++ from codebase (c++ runtime doesn't play nice with postgres runtime)
Nice not needing text parsing for postgres/clickhouse value conversions
> I'd like to open another topic about the usage of LLM for review, auditing and security purposes, but I think this is a very separate thread, and we'll open discussions at the user conference before any formal discussions.
nitpick: this library requires consumer give io callbacks (potentially through the included clickhouse-client.h header), or use the sans-io interface (which clickhouse-c-rs[1] uses to implement tokio layer), which makes it capable of talking over native tcp protocol, http, or stdin/stdout (clickhouse local). ClickHouse has both native protocol[2] & native format[3]
reply