Newest at the top
| 2026-04-03 03:27:49 +0000 | merijn | (~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 245 seconds) |
| 2026-04-03 03:21:18 +0000 | merijn | (~merijn@host-cl.cgnat-g.v4.dfn.nl) merijn |
| 2026-04-03 03:10:10 +0000 | merijn | (~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 248 seconds) |
| 2026-04-03 03:07:15 +0000 | <mesaoptimizer> | will reply in #haskell-offtopic. |
| 2026-04-03 03:06:46 +0000 | <geekosaur> | the kinds of messes they produce fit that model very well |
| 2026-04-03 03:06:17 +0000 | <geekosaur> | LLMs only use the LLM part to interpret prompts and reformat results; the actual work, as best I can determine having read lots of them, is actually generated via Markov chains |
| 2026-04-03 03:06:07 +0000 | <EvanR> | your point started out as the article is a dangerous waste of time but we're still talking about it |
| 2026-04-03 03:05:55 +0000 | merijn | (~merijn@host-cl.cgnat-g.v4.dfn.nl) merijn |
| 2026-04-03 03:05:28 +0000 | <geekosaur> | I for one am kinda confused by how you jumped straight to "must be an LLM". there _are_ some clear indications thereof, but your complaints seem more in the "I don't like its style" category |
| 2026-04-03 03:05:27 +0000 | <mesaoptimizer> | anyway, let's move on |
| 2026-04-03 03:04:44 +0000 | <mesaoptimizer> | this is probably an offtopic thing, but in short, I really really do not think it is a good idea to extend this intuition to text generated by LLMs outright or even partially. |
| 2026-04-03 03:03:02 +0000 | <mesaoptimizer> | and yeah I agree, and have found some Haskell papers even more lucid than any introductory textbook, especially the 1997 Wadler / Blott one for typeclasses |
| 2026-04-03 03:02:44 +0000 | <mesaoptimizer> | yeah, I'm confused by the reaction of you guys just now |
| 2026-04-03 03:02:34 +0000 | <EvanR> | sure |
| 2026-04-03 03:02:22 +0000 | <EvanR> | just in general? |
| 2026-04-03 03:02:14 +0000 | <EvanR> | what's this in relation to |
| 2026-04-03 03:01:45 +0000 | <mesaoptimizer> | or a sort of "hey, look you have to put in the work if you want to master this" |
| 2026-04-03 03:01:27 +0000 | <mesaoptimizer> | I think the thing you wish to encourage is "read the docs" |
| 2026-04-03 03:01:19 +0000 | <monochrom> | Haven't you heard? Those LLMs that have learned from history are doomed to repeat it! |
| 2026-04-03 03:00:44 +0000 | <geekosaur> | ^ |
| 2026-04-03 03:00:20 +0000 | <Leary> | mesaoptimizer: LLMs do that because they ate a huge amount of text written by humans who did that. |
| 2026-04-03 03:00:17 +0000 | <EvanR> | butlerian jihad! |
| 2026-04-03 02:59:42 +0000 | <monochrom> | "I do not trust it when a computer says 1+1=2 because it's a stupid computer!" |
| 2026-04-03 02:59:37 +0000 | merijn | (~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 272 seconds) |
| 2026-04-03 02:59:37 +0000 | <mesaoptimizer> | okay, *at least* you aren't saying I'm wrong, I do appreciate that lol |
| 2026-04-03 02:58:57 +0000 | <monochrom> | or perhaps ad machinem? |
| 2026-04-03 02:58:54 +0000 | <EvanR> | that article isn't about LLMs or AI at all so |
| 2026-04-03 02:58:44 +0000 | <mesaoptimizer> | erm, I have been paid to do research engineer work on neural networks, and have worked with researchers now at DM and Anthropic |
| 2026-04-03 02:58:39 +0000 | <monochrom> | ad machina >:) |
| 2026-04-03 02:57:31 +0000 | <EvanR> | we need a new latin fallacy like ad hominem but for attacking the LLM |
| 2026-04-03 02:57:22 +0000 | <mesaoptimizer> | it is quite common for an LLM to add a concrete, supposedly humorous exageration as part of its triadic description for something, and you can see it with "a small municipal government's worth of bookkeeping". |
| 2026-04-03 02:56:13 +0000 | <mesaoptimizer> | sidenote: "Your database layer uses connection pooling, retry logic, and mutable state internally. Your cache uses concurrent mutable maps. Your HTTP client probably has circuit breakers, pooled connections, and a small municipal government's worth of bookkeeping." this is a clear indicator that an LLM was used to write this essay |
| 2026-04-03 02:55:45 +0000 | bitdex | (~bitdex@gateway/tor-sasl/bitdex) bitdex |
| 2026-04-03 02:54:56 +0000 | merijn | (~merijn@host-cl.cgnat-g.v4.dfn.nl) merijn |
| 2026-04-03 02:54:22 +0000 | weary-traveler | (~user@user/user363627) user363627 |
| 2026-04-03 02:45:39 +0000 | <mesaoptimizer> | EvanR: it started off quite interesting, yes, which is why I even put in the effort to ask about the thing that confused me, so yes, I am reading onwards. |
| 2026-04-03 02:45:00 +0000 | arandombit | (~arandombi@user/arandombit) arandombit |
| 2026-04-03 02:45:00 +0000 | arandombit | (~arandombi@2a02:2455:8656:7100:cd4b:38a2:fba4:622b) (Changing host) |
| 2026-04-03 02:45:00 +0000 | arandombit | (~arandombi@2a02:2455:8656:7100:cd4b:38a2:fba4:622b) |
| 2026-04-03 02:44:56 +0000 | <mesaoptimizer> | ... sorry, that was for davean |
| 2026-04-03 02:44:47 +0000 | <mesaoptimizer> | EvanR: I disagree about that claim when in a cognitively adverserial environment |
| 2026-04-03 02:44:15 +0000 | merijn | (~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 255 seconds) |
| 2026-04-03 02:44:02 +0000 | <davean> | Yah the obligation is on you to actually think clearly about it. |
| 2026-04-03 02:43:57 +0000 | <EvanR> | (there's a lot in there that is haskell specific, but as far as groundbreaking insights maybe not many) |
| 2026-04-03 02:43:23 +0000 | <EvanR> | otherwise don't bother |
| 2026-04-03 02:43:17 +0000 | <EvanR> | ok if you're going to analyze the article then yeah maybe read it |
| 2026-04-03 02:42:58 +0000 | arandombit | (~arandombi@user/arandombit) (Ping timeout: 248 seconds) |
| 2026-04-03 02:42:56 +0000 | <mesaoptimizer> | so it still stands. It is not specific to Haskell. |
| 2026-04-03 02:42:30 +0000 | <mesaoptimizer> | Leary: perhaps I misused the word, but my point was about semantic safety, in the sense of Benjamin Pierce's definition in TAPL |
| 2026-04-03 02:42:19 +0000 | <EvanR> | as you wish |