Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

github.com

Post reply on HN
Print view View original

31–40 of 42 posts

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#31

Post by renato_shira »

tibbar wrote: post #19
swyx wrote: post #15

Earlier quoted context omitted.

how exactly is adding a stored procedure as an agent mind bending

I can only speak for my own mind ;) but the most advanced thing I'd seen prior in this regard was Google Sheets' =AI function, which is pretty convenient (if awkward) when you want to map values to LLM output. What I specifically found "mind-bending" about this is that I don't have a clear concept of the limits of what an agent can do . In the limit case, it's basically like an independent employee, right?. So the co…

[flagged]

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#32

Post by worldsavior »

brunoqc wrote: post #29
rel_ic wrote: post #23

We need your help! Can you please use your creativity to build resilience to climate change in your community instead of experimenting with more ways to spend computing power?

The solution is to tax the rich. But we won't.

Until YOU get rich.

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#33

Post by cpursley »

maxbond wrote: post #30
cpursley wrote: post #18

Earlier quoted context omitted.

Yes, and I imagine pgclaw would pair well with pgmq and pg_cron for scheduled work. Postgres really is enough: https://postgresisenough.dev

Interesting to hear you say that, I was thinking (but hadn't said) that using WalEx to dispatch to some workers where the agent lived would be a better solution. The worker would then update the row (or more likely insert a new one in a different table with more constraints/different columns). I would be curious to hear what advantage you see in a `claw` type/`agent` column? I can't make heads or tails of it but I re…

You could probably use listen/subscribe trigger to accomplish that.

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#34

Post by SOLAR_FIELDS »

thatwasunusual wrote: post #22
4ndrewl wrote: post #16

Earlier quoted context omitted.

It's similar to when we wrote all our business logic in eg pl/sql, stored procedures etc. Seems attractive at first, but it breaks separation of concerns, becomes difficult to test etc.

> It's similar to when we wrote all our business logic in eg pl/sql [...] What do you mean with "when"? /s I dread companies who still have logic in their databases when it's not necessary.

The real fun begins when you encounter a system where someone thought it was a good idea to store source code in the database rows.

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#37

Post by tibbar »

swyx wrote: post #25
tibbar wrote: post #19

Earlier quoted context omitted.

I can only speak for my own mind ;) but the most advanced thing I'd seen prior in this regard was Google Sheets' =AI function, which is pretty convenient (if awkward) when you want to map values to LLM output. What I specifically found "mind-bending" about this is that I don't have a clear concept of the limits of what an agent can do . In the limit case, it's basically like an independent employee, right?. So the co…

ok nice reply. i think i was where you were in 2021 around doing stuff in sprocs. i think pple generally follow a cycle of going overexcited about throwing everything in the database and then going "actually the database is a pretty bad production compute environment" and re-separating concerns back to different levels. use sprocs lightly for simple fast stateless things. every other attempt at stuffing a lot of comp…

Oh, like, I wouldn't actually use this specific implementation. I used to work at a shop with thousands of lines of Oracle triggers that you had to edit inline in the web browser with no version control and I shudder to think of returning again.

I'm more interested in the data flow. exa.ai got famous for promising search with massively parallel execution of LLMs on candidate results. In practice, it's never worked that well for me, but the model is very cool and has worked for me e.g. in open source work, searching for bugs across files.

Mapping N items to "N agents with state" feels like an absurdly powerful construct to me. Maybe this is just a well-known pattern that everyone has seen already, but given how much better agents have gotten in the past year, crossing the threshold from "toy" to "arguably superhuman" on many tasks, I think it just hits different.

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#38

Post by jmaw »

What does it mean to put an agent inside of a PG DB? Is PG doing the actual computing/inference (does it tie to GPU), or is PG just storing the state of the agents neural net (is that a thing, it seems like it would be).

Maybe I'm strictly too stupid to even parse the concept, but I don't understand what I'm looking at one bit.

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#39

Post by swyx »

tibbar wrote: post #37
swyx wrote: post #25

Earlier quoted context omitted.

ok nice reply. i think i was where you were in 2021 around doing stuff in sprocs. i think pple generally follow a cycle of going overexcited about throwing everything in the database and then going "actually the database is a pretty bad production compute environment" and re-separating concerns back to different levels. use sprocs lightly for simple fast stateless things. every other attempt at stuffing a lot of comp…

Oh, like, I wouldn't actually use this specific implementation. I used to work at a shop with thousands of lines of Oracle triggers that you had to edit inline in the web browser with no version control and I shudder to think of returning again. I'm more interested in the data flow. exa.ai got famous for promising search with massively parallel execution of LLMs on candidate results. In practice, it's never worked th…

ok gotcha. yeah i guess my background with temporal.io got me used to "every workflow instance can have a shit ton of long running state that gets persisted and rehydrated at will". check those out if you like N:N+state, whether or not it includes agents is an impl detail

Re: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

#40

Post by tibbar »

swyx wrote: post #39
tibbar wrote: post #37

Earlier quoted context omitted.

Oh, like, I wouldn't actually use this specific implementation. I used to work at a shop with thousands of lines of Oracle triggers that you had to edit inline in the web browser with no version control and I shudder to think of returning again. I'm more interested in the data flow. exa.ai got famous for promising search with massively parallel execution of LLMs on candidate results. In practice, it's never worked th…

ok gotcha. yeah i guess my background with temporal.io got me used to "every workflow instance can have a shit ton of long running state that gets persisted and rehydrated at will". check those out if you like N:N+state, whether or not it includes agents is an impl detail

Haha, I guess we see this in reverse: I see the specific framework as the implementation detail (I use, and enjoy, temporal!) I think it's the part about automatically launching a metric ton of agents that is (to use the term again) mind-bending to me.
Post reply on HN