Post ApfLimrJngy4FbGXtw by sun@shitposter.world
(DIR) More posts by sun@shitposter.world
(DIR) Post #ApdfGssBSNoxYritFI by david_chisnall@infosec.exchange
2025-01-01T11:31:41Z
5 likes, 4 repeats
A lot of the current hype around LLMs revolves around one core idea, which I blame on Star Trek:Wouldn't it be cool if we could use natural language to control things?The problem is that this is, at the fundamental level, a terrible idea. There's a reason that mathematics doesn't use English. There's a reason that every professional field comes with its own flavour of jargon. There's a reason that contracts are written in legalese, not plain natural language. Natural language is really bad at being unambiguous.When I was a small child, I thought that a mature civilisation would evolve two languages. A language of poetry, that was rich in metaphor and delighted in ambiguity, and a language of science that required more detail and actively avoided ambiguity. The latter would have no homophones, no homonyms, unambiguous grammar, and so on.Programming languages, including the ad-hoc programming languages that we refer to as 'user interfaces' are all attempts to build languages like the latter. They allow the user to unambiguously express intent so that it can be carried out. Natural languages are not designed and end up being examples of the former.When I interact with a tool, I want it to do what I tell it. If I am willing to restrict my use of natural language to a clear and unambiguous subset, I have defined a language that is easy for deterministic parsers to understand with a fraction of the energy requirement of a language model. If I am not, then I am expressing myself ambiguously and no amount of processing can possibly remove the ambiguity that is intrinsic in the source, except a complete, fully synchronised, model of my own mind that knows what I meant (and not what some other person saying the same thing at the same time might have meant).The hard part of programming is not writing things in some language's syntax, it's expressing the problem in a way that lacks ambiguity. LLMs don't help here, they pick an arbitrary, nondeterministic, option for the ambiguous cases. In C, compilers do this for undefined behaviour and it is widely regarded as a disaster. LLMs are built entirely out of undefined behaviour.There are use cases where getting it wrong is fine. Choosing a radio station or album to listen to while driving, for example. It is far better to sometimes listen to the wrong thing than to take your attention away from the road and interact with a richer UI for ten seconds. In situations where your hands are unavailable (for example, controlling non-critical equipment while performing surgery, or cooking), a natural-language interface is better than no interface. It's rarely, if ever, the best.
(DIR) Post #ApdxXuK37SeI9e1XuK by jarkman@chaos.social
2025-01-01T12:15:00Z
0 likes, 0 repeats
@david_chisnall I'm not so sure. I often express myself in natural language to ask people to do things, and that usually works out pretty well. So it's possible in principle, it's just not something that computers can do yet. Maybe one day they will.
(DIR) Post #ApdxXvZgSokW2QLXuq by wolf480pl@mstdn.io
2025-01-01T16:09:30Z
1 likes, 0 repeats
@jarkman @david_chisnall Because people actually do have a synchronized model of how other humans' brains works, and those who know you have a model that matches your particular brain. I think it's called "mirror neurons".
(DIR) Post #ApeRwIL2TeyEDJ21nU by baltauger@mastodon.gamedev.place
2025-01-01T14:12:19Z
1 likes, 0 repeats
@david_chisnallThere is a recent game called Chants of Senaar that explores this "use-based language": a city where each caste (priests, soldiers, artists, scientists) have their own language that you need to learn, each language fit for expressing different concepts that were alien to other caste.
(DIR) Post #ApeRwJ8fV8fYhEFf9c by david_chisnall@infosec.exchange
2025-01-01T14:17:54Z
2 likes, 0 repeats
@baltauger In linguistics, the Whorf-Sapir hypothesis, also known as the Linguistic Relativity hypothesis, argues that language constrains thought. This was the idea behind Orwell's Newspeak. The strong variant argues that you cannot think an idea that your language cannot express (the goal of Newspeak), the weak variant argues that language guides thought. The strong variant is largely discredited because it turns out that humans are really good at just making up new language for new concepts. The weak variant is supported to varying degrees.I keep trying to persuade linguists to study it in the context of programming languages, where humans are limited in the things that they can extend because a compiler / interpreter also needs to understand the language. I think there are some very interesting research results to be found there.
(DIR) Post #ApeRxXdp4CkPxrPcGW by fluchtkapsel@nerdculture.de
2025-01-01T12:55:07Z
2 likes, 1 repeats
@david_chisnall Natural language interfaces are akin to magic. It's all under the assumption that the intent is somehow, magically recognised. Funnily, there are cautionary tales re magic addressing exactly this aspect. Almost all stories involving wishes turn the phrasing against the one expressing their wishes (see djinns, fairies, etc.).
(DIR) Post #ApeRxgc1iFetmtdoDQ by ColinTheMathmo@mathstodon.xyz
2025-01-01T15:11:15Z
2 likes, 0 repeats
@lambdasierra @david_chisnall In "The Moon is a Harsh Mistress" they mention "loglan" (which is now lojban).There are some who think that would do the job.
(DIR) Post #ApeRxjaMet6z0bt1Xc by RogerBW@discordian.social
2025-01-01T19:30:04Z
2 likes, 0 repeats
@ColinTheMathmo @lambdasierra @david_chisnall Sadly it mostly turns out to be too computer for most humans and too human for computers.
(DIR) Post #ApeRxtZfWKUrzLdbqS by ErikJonker@mastodon.social
2025-01-01T12:00:49Z
0 likes, 0 repeats
@david_chisnall ...that's also one of it's strengths, language is a completely different "beast" then math. Comparing it is useless. Language fulfills different functions then math. But just as important for human beings.
(DIR) Post #ApeRxuMEblLSPyMOXo by resuna@ohai.social
2025-01-01T14:40:09Z
0 likes, 0 repeats
@ErikJonker @david_chisnall That's the point. Giving directions to a machine requires math. Using the term "language" to refer to machine instructions has led people down the wrong path over and over again and led to monstrosities like COBOL and Perl and "Congratulations, you have decided to clean the elevator!"
(DIR) Post #ApeRxusUfp9K21S9pI by ErikJonker@mastodon.social
2025-01-01T14:44:40Z
1 likes, 0 repeats
@resuna @david_chisnall cobol is not a monstrosity as a programming language, it’s ofcourse legacy
(DIR) Post #ApeRxvBzVKkH0UZjDU by ErikJonker@mastodon.social
2025-01-01T14:46:50Z
0 likes, 0 repeats
@resuna @david_chisnall …a natural language interface for a computer can have enormous benefits, a good example is an educational context, you can interact, ask question’s etc in a way not possible before
(DIR) Post #ApeRxvNgnq6Ram34S0 by resuna@ohai.social
2025-01-01T14:50:39Z
1 likes, 0 repeats
@ErikJonker @david_chisnall My first job was programming in COBOL before it was legacy. It is terrible. It always was terrible. It's not a natural language, it's not ambiguous, but trying to make it look like a natural language was an unmitigated disaster at every level. The same is true of Perl's "linguistic" design. Even just pretending to be a natural language spawns monstrosities.
(DIR) Post #ApeRxvgTfz8EX2q4jg by resuna@ohai.social
2025-01-01T14:51:33Z
1 likes, 0 repeats
@ErikJonker @david_chisnall Even communicating with other humans in natural language leads to confusion, and humans are much much better at dealing with ambiguity than any computer.
(DIR) Post #ApeRxxI5hcoTVzRd0C by jhavok@mastodon.social
2025-01-01T19:25:17Z
2 likes, 0 repeats
@ErikJonker @resuna @david_chisnall I deal with people's questions every day, and much of the time they aren't even sure what they are asking for. It takes a good deal of drilling down to get to what they need to know. A lot of what is involved is figuring out what they need to know to find out what they want to know. It's difficult for a human with shared experience, I'm skeptical that an LLM could manage it.
(DIR) Post #ApeRxxNPNr4BmTvsI4 by ErikJonker@mastodon.social
2025-01-01T16:43:44Z
0 likes, 0 repeats
@resuna @david_chisnall it is extremely stable and durable for sure, ask any financial institution 😃
(DIR) Post #ApeRxxsxUYItMKh4T2 by jhannafin@mastodon.sdf.org
2025-01-01T19:41:11Z
1 likes, 0 repeats
@ErikJonker @resuna @david_chisnall OK, but that's not because of COBOL. You could write something durable and stable in any programming language. Financial software is written in COBOL because that was the language of the mainframe at the time. The fact that it's still largely in COBOL is because it's expensive to rewrite, the returns on a rewrite are hard to quantify, and the risks are huge.
(DIR) Post #ApeRxypnxlNKIqE4Bs by ErikJonker@mastodon.social
2025-01-01T14:57:23Z
0 likes, 0 repeats
@resuna @david_chisnall ofcourse but current AI models can provide a level of education that scales easily, it will supplement humans in their roles and sometimes replace them. Current models can perfectly help students with high school math, even with some ambiguity
(DIR) Post #ApeRxzab9mo0dy7R7w by naught101@mastodon.social
2025-01-01T21:24:29Z
1 likes, 0 repeats
@ErikJonker @resuna @david_chisnall Huh? Perfectly?There have been multiple instances of people showing LLMs getting answers wrong to the most basic arithmetic problems. That's not a bug, it's an inherent feature of the model, which draws meaning from language only and has no concept of maths.That incorrectness can only get more likely as math problems get more complex. And the more complex it gets, the harder it is for humans to detect the errors.How is that perfect for education?
(DIR) Post #ApeRy0S7wlcjJzABYu by ErikJonker@mastodon.social
2025-01-01T21:35:03Z
1 likes, 0 repeats
@naught101 @resuna @david_chisnall as a support tooll during homework, where it can give additional explanation, I see a bright future for the current best models (for highschool level assignments) , for text based tasks they are even better (not strange for LLMs) . Ofcourse people have to learn to check and not fully trust, at the same time there is a lot of added value. It's my personal/micro observation but i see it confirmed in various papers
(DIR) Post #ApfGDqsWJ66Dy7G25I by icedquinn@blob.cat
2025-01-02T07:24:49.138362Z
0 likes, 0 repeats
programming started with english but the computers were too stupid
(DIR) Post #ApfLimrJngy4FbGXtw by sun@shitposter.world
2025-01-02T08:26:28.838677Z
0 likes, 1 repeats
@david_chisnall I’m using llms for a variety of uses every day now and they’re great, turns out you don’t need perfection a lot of the time
(DIR) Post #ApfaBXII9Fu1jVU8si by clacke@libranet.de
2025-01-02T10:26:19Z
0 likes, 0 repeats
Time to share this lovely @CommitStrip again!commitstrip.com/en/2016/08/25/…@david_chisnall
(DIR) Post #ApgNOLDPGPcBn1w4rw by feld@friedcheese.us
2025-01-02T17:21:22.746351Z
0 likes, 0 repeats
@david_chisnall >> Wouldn't it be cool if we could use natural language to control things?> The problem is that this is, at the fundamental level, a terrible idea.This is a terrible take and you should really know better. It's not different than chastising people who use higher level programming languages or Dreamweaver to make a website instead of studying HTML.We can all agree that e.g., setting down a person with no development experience and asking them to design a missile defense system for your country using natural language is a terrible idea.We should all be able to agree that giving people a way to use natural language to build little apps, tools, and automations that solve problems nobody is going to build a custom solution for is a good thing.
(DIR) Post #ApgNOMRyfirfcVlEDg by david_chisnall@infosec.exchange
2025-01-02T19:44:23Z
1 likes, 0 repeats
@feld This is a terrible take and you should really know better. It's not different than chastising people who use higher level programming languages or Dreamweaver to make a website instead of studying HTML.I feel like you didn’t read past the quoted section before replying with a needlessly confrontational reply.It is very different. If you give someone a low-code end-user programming environment, they have a tool the helps them to unambiguously express their intent. It gives them a tool to do so concisely, often more concisely (at the expense of generality), which empowers the user. This is a valuable thing to do.We should all be able to agree that giving people a way to use natural language to build little apps, tools, and automations that solve problems nobody is going to build a custom solution for is a good thing.No, I disagree with that. Giving them a natural-language interface and you remove agency from them. The system, not the user, is responsible for filling in the blanks. And the system does so in a way that does not permit the user to learn. Rather than using the tool badly and then improving as a result of their failure, the system fills in the blanks in arbitrary ways.A natural-language interface and an easy-to-learn interface are not the same thing. There is enormous value in creating easy-to-learn interfaces that empower users but giving them interfaces that use natural language is not the best (or even a very good) way of doing this.
(DIR) Post #ApgNONJ9U1OoHQdh6O by feld@friedcheese.us
2025-01-02T20:16:48.549979Z
0 likes, 0 repeats
@david_chisnall > No, I disagree with that. Giving them a natural-language interface and you remove agency from them.This just seethes with "no, everyone should learn to code" energy. People should not need to learn to code to do these things.You are thinking about this from inside your bubble. Perfect is the enemy of good.
(DIR) Post #ApgNOOS3EQ6zpJoJc0 by dictatordave@poa.st
2025-01-02T20:19:52.644974Z
0 likes, 1 repeats
@feld @david_chisnall with cheap labor and ai, the 1st world choder is sperging because there is an ever more limited market available to make a livingits like when cars took out other modes of transportationi'm a cad guy and know my industry is just waiting to be buried, but some computer nerds are fucking delusional
(DIR) Post #ApiQizrMXwtdoh5NL6 by jhavok@mastodon.social
2025-01-02T23:27:25Z
1 likes, 0 repeats
@wakame @FSonder @resuna @Disputatore @ErikJonker @david_chisnall Lots of woowoos claim that quantum effects justify their woo. But they don't have the math.
(DIR) Post #Av6H0mXod9OGbmh4zY by jeffcliff@shitposter.world
2025-06-13T21:31:25.380835Z
1 likes, 1 repeats
@david_chisnall COBOL predated star trek by almost a decade. And it was late to the game of being as close to natural language as technology would allow. FLOW-MATIC also was in a push in that direction and, realistically, Saint Turing was already thinking along those lines in 'Computing Machinery and Intelligence' and earlier. Realistically the idea of using natural language with computers goes right to the beginning with Lady Ada and her poetic science