Newest at the top
| 2025-11-26 21:03:15 +0100 | Shark8 | (~Shark8@c-174-56-102-109.hsd1.nm.comcast.net) |
| 2025-11-26 21:03:04 +0100 | Shark8 | (~Shark8@c-174-56-102-109.hsd1.nm.comcast.net) (Read error: Connection reset by peer) |
| 2025-11-26 20:53:10 +0100 | pavonia | (~user@user/siracusa) siracusa |
| 2025-11-26 20:51:50 +0100 | statusbot3 | (~statusbot@ec2-34-198-122-184.compute-1.amazonaws.com) (Remote host closed the connection) |
| 2025-11-26 20:51:34 +0100 | statusbot | (~statusbot@ec2-34-198-122-184.compute-1.amazonaws.com) statusbot |
| 2025-11-26 20:51:19 +0100 | <EvanR> | based |
| 2025-11-26 20:48:55 +0100 | peterbecich | (~Thunderbi@172.222.148.214) (Ping timeout: 240 seconds) |
| 2025-11-26 20:40:53 +0100 | <monochrom> | Hey speaking of "synergy" business tactics. I saw this beautiful scene at a mall: A gym and a dessert pastry bakery next to each other. |
| 2025-11-26 20:39:58 +0100 | sindu | (~sindu@2.148.32.207.tmi.telenormobil.no) |
| 2025-11-26 20:39:01 +0100 | <int-e> | (and inbetween people break a few legs) |
| 2025-11-26 20:38:27 +0100 | <int-e> | hey picture moment: first you sell them agile coding, then you sell the crutches (LLMs) |
| 2025-11-26 20:37:54 +0100 | <monochrom> | (Don't worry, I denounce back those hipster agile fads.) |
| 2025-11-26 20:37:17 +0100 | <monochrom> | Leary: That sounds dangerously close to the water fall model that every hipster agile coder has denounced. |
| 2025-11-26 20:36:24 +0100 | EvanR | (~EvanR@user/evanr) EvanR |
| 2025-11-26 20:36:04 +0100 | EvanR | (~EvanR@user/evanr) (Remote host closed the connection) |
| 2025-11-26 20:35:54 +0100 | <monochrom> | About current AI ("AI") and the training data: Those LLMs that have learned from history are doomed to repeat it. >:) |
| 2025-11-26 20:33:16 +0100 | Googulator89 | (~Googulato@84-236-53-137.pool.digikabel.hu) |
| 2025-11-26 20:33:05 +0100 | peterbecich | (~Thunderbi@172.222.148.214) peterbecich |
| 2025-11-26 20:32:58 +0100 | Googulator89 | (~Googulato@2a01-036d-0106-4ad8-f42e-6d50-f4ab-2863.pool6.digikabel.hu) (Quit: Client closed) |
| 2025-11-26 20:30:05 +0100 | tromp | (~textual@2001:1c00:3487:1b00:c5b7:b8d9:7db7:74e1) |
| 2025-11-26 20:17:19 +0100 | sindu | (~sindu@2.148.32.207.tmi.telenormobil.no) (Ping timeout: 240 seconds) |
| 2025-11-26 20:15:56 +0100 | Googulator45 | (~Googulato@2a01-036d-0106-4ad8-f42e-6d50-f4ab-2863.pool6.digikabel.hu) (Quit: Client closed) |
| 2025-11-26 20:15:46 +0100 | Googulator89 | (~Googulato@2a01-036d-0106-4ad8-f42e-6d50-f4ab-2863.pool6.digikabel.hu) |
| 2025-11-26 20:14:21 +0100 | <EvanR> | it sounds like that has a chance of running locally |
| 2025-11-26 20:13:23 +0100 | <Leary> | ing random errors and holes in existing programs, and more collected every time a programmer accepts/rejects an output... |
| 2025-11-26 20:13:22 +0100 | <Leary> | Imo, to make good use of AI in programming we just need an iterative approach with both the human and the compiler in the loop. Instead of trying to "engineer" prompts for LLMs trained to replicate all text in existence, we use smaller, specialised machines trained on the much richer semantic data produced by the compiler. One for type errors, one filling holes from context, one fixing bugs given a test failure, etc. Initial data can be gathered by putt |
| 2025-11-26 20:05:57 +0100 | <EvanR> | the soliton radar is made from currently existing technology |
| 2025-11-26 20:04:58 +0100 | <haskellbridge> | <sm> 👍️ yes I mean the technology when its available |
| 2025-11-26 20:00:09 +0100 | <EvanR> | that can't go on |
| 2025-11-26 20:00:02 +0100 | <EvanR> | which has high negative profits |
| 2025-11-26 19:59:46 +0100 | <EvanR> | as long as it still exists in the current form |
| 2025-11-26 19:59:24 +0100 | <haskellbridge> | <sm> I think it's pretty much settled by now that AI can, is, and will be increasingly helpful in programming generally speaking |
| 2025-11-26 19:59:07 +0100 | <EvanR> | you could imagine someone like this shilling AI code that is just awful |
| 2025-11-26 19:58:44 +0100 | <EvanR> | so pick your authorities carefully |
| 2025-11-26 19:58:36 +0100 | <EvanR> | after they cheated |
| 2025-11-26 19:58:23 +0100 | <EvanR> | "an authority" is also highly subjective... I was just caught up on this 4 year old drama involving a minecraft speed runner with a hoard of fans defending them at all costs |
| 2025-11-26 19:57:29 +0100 | <Square3> | But yeah, I get that it's highly dependent on task / tools. Here I was mostly curious on the general view of the concept. |
| 2025-11-26 19:57:23 +0100 | <haskellbridge> | <sm> oops irc, I shouldn't edit |
| 2025-11-26 19:57:01 +0100 | <haskellbridge> | <sm> * code, which prompting strategy |
| 2025-11-26 19:54:27 +0100 | <Square3> | sm, I've taken the lazy approach and wait for a signal of AI's usefulness from an authority. Meanwhile I'll stick to some low effort free service. |
| 2025-11-26 19:52:33 +0100 | <haskellbridge> | <sm> Square3 I don't advocate heedless ai use, but I think you must try it yourself to know. It also needs to be qualified - which AI, which AI-based coding tools, which kind of code |
| 2025-11-26 19:52:27 +0100 | target_i | (~target_i@user/target-i/x-6023099) target_i |
| 2025-11-26 19:51:54 +0100 | chele | (~chele@user/chele) (Remote host closed the connection) |
| 2025-11-26 19:51:12 +0100 | <geekosaur> | or wants to replace employees they have to pay with AI they don't |
| 2025-11-26 19:50:44 +0100 | <Square3> | Interesting to hear |
| 2025-11-26 19:48:51 +0100 | <int-e> | "for themselves" - I mean nobody wants to read the results |
| 2025-11-26 19:48:15 +0100 | <int-e> | I feel that when it comes to writing, nobody wants AI for themselves; people think (or hope) that the output is good enough to sell to others for money. |
| 2025-11-26 19:47:48 +0100 | <EvanR> | harry potter fanfiction has a different standard than uh |
| 2025-11-26 19:47:23 +0100 | <EvanR> | it depends on who is judging the quality |
| 2025-11-26 19:47:02 +0100 | <haskellbridge> | <Zemyla> AI isn't good at literature or poetry either. |