| ▲ | sambejk 7 hours ago |
| I like the blog and fully agree that you should be able to make a report without AI usage. On the other hand, it is probably not bad to let AI check for grammar and spelling mistakes. In this blog, I can read at least one: "right" instead of "write". It could be an amazing reviewer to bounce ideas off and catch any glaring errors |
|
| ▲ | PMunch 7 hours ago | parent | next [-] |
| There's certainly a fine lead to tread here. Sure, AI is great at catching spelling mistakes, but it's also great at normalizing and hyper-polishing your work, erasing your own voice from it. There was an article [1] shared recently on here that talks about this and how the author uses AI but has a strict rule to _never_ take a sentence from the AI. Getting direction and feedback, as well as spell checking (although there might be more efficient ways of just getting spell-check than a full blown LLM) is fine, but it's very easy to let the AI voice take over. [1] https://sockpuppet.org/blog/2026/09/17/how-to-write-with-an-... |
| |
| ▲ | alex43578 7 hours ago | parent [-] | | An engineering report shouldn’t really have a voice, just like a manual or a press-pool news report. It’s not the great American novel, and voices, mistakes, or quirks all detract from efficiently conveying the information. I’m not saying Claude’s writing is good or clear (it’s often not), but for a lot of professional communication, the message shouldn’t be secondary to voice. |
|
|
| ▲ | benrutter 7 hours ago | parent | prev | next [-] |
| Do you use AI for grammar errors? I've never thought to question standard grammar tools. Do they work better for you? Are there trade offs? Obviously AI can comment on style and structure, I just hadn't thought about grammar before as a use case. |
| |
| ▲ | hxelk1 6 hours ago | parent | next [-] | | I do use LLMs for stuff that gets published. My prompt is something like: > Point out spelling, grammar and style errors in the following text. Do not touch the text, only provide a list of corrections with an explanation for each. I then go and manually edit my text. I'm not a native English speaker, and this has been very valuable in helping me unlearn some of my favorite flops. | |
| ▲ | IshKebab 6 hours ago | parent | prev [-] | | Standard modern grammar tools do use AI. The 00s era grammar checkers were useless trash. But yeah I feel like they are perfectly sufficient for spelling and grammar. You don't need an LLM. But I would probably still at least see what an LLM says anyway. Occasionally they have good writing suggestions and it's not really any effort to try. |
|
|
| ▲ | paganel 7 hours ago | parent | prev | next [-] |
| > AI check for grammar and spelling mistakes To the contrary, in this very sad AI age we're now living seeing genuinely human grammar mistakes is refreshing. Perfect-ness is the enemy of human ingenuity. Later edit: To quote an Austrian Communist Party member from back in the early '30s (even though the quote was made in the late '50s - 'early '60s): > As machines become more and more efficient and perfect, so it will become clear that imperfection is the greatness of man. [1] [1] https://en.wikipedia.org/wiki/Ernst_Fischer_(writer) |
| |
| ▲ | syshyk 6 hours ago | parent | next [-] | | I honestly don't see that grammar mistakes that that much of a problem to start with. It only matters if what you are writing would be misunderstood, no? The rules of English are a complete mess anyway, not to mention region specific. I really don't care any more. I have started to argue that punctuation only matters if you strip it from sentences after the fact, any of these examples people give for why its necessary from lack of capitalisation can be removed by writing without that in mind. An on an AI specific note that bridges language... I have colleagues here on AI courses, in the UK, they have to go through some English and Maths tests. It's meant for young apprentices, a complete government subsidy grab if you ask me, even though they're a seasoned professional. There is a huge amount of Americanisms in there, and the fact it refuses a specific type of " marking it as wrong, the Oxford comma argument etc - so I wouldn't trust AI(LLMs) to be correct either. I am useless at writing long documents, so toyed with trying to get LLMs to reflow them without changing anything (I doubt it), but time and time again it just turns it into worse tosh. I cannot stand reading the long winded emails and "policy documents" that someone has AI spun up, and likely not even read. Working with people that don't put in the work is pretty shit. | |
| ▲ | alex43578 7 hours ago | parent | prev [-] | | Ahh, the wonderful value of human imperfection: deaths to medical errors, false convictions in courts, and the myriad everyday mistakes in judgement. If human ingenuity invents a self-driving car, will we long for the days of driving ourselves into a tree just because we miss being imperfect drivers? | | |
| ▲ | xigoi 6 hours ago | parent | next [-] | | You’re spitting in the face of the numerous people who have been falsely convicted by LLMs. | | |
| ▲ | DonHopkins 4 hours ago | parent [-] | | AHEM -- Or by humans just pulling made-up bullshit out of their asses and trying to pass it off as arguments without any citations. If "numerous people" have been falsely convicted by LLMs, name them and cite the cases, before trying to falsely convict other people of spitting in faces youself. "You’re spitting in their faces" isn't a citation, it's a histrionic attempt to emotionally manipulate people into swallowing your unsupported claim. |
| |
| ▲ | syshyk 6 hours ago | parent | prev [-] | | Sounds like a straw man to me? The quote above generally points to the fact that our mistakes and basically hunches is what drives change and innovation. And I do feel a bit sickly business saying that. AI is spinning up some interesting new things (yes, ill just call it things, enjoy) but I can only feel that what we're seeing is the wisdom of the crowed as the LLM averages our thoughts as they currently stand. This can only happen once. | | |
| ▲ | alex43578 6 hours ago | parent [-] | | 1) I don’t see that in the quote. To me it reads as a nostalgia for human imperfection: an impressionist painting is inherently more valuable than a photograph of the scene, for example. 2) LLMs have clearly surpassed the “wisdom of the crowd”. Their abilities are spiky, but I guarantee the latest frontier model is more intelligent than 80% of people across a number of domains. For math, given the ability to answer questions that have gone unanswered for years or decades, it’s clearly smarter than 99% of people. Calculators were not a high watermark for our ability to do math. Making mistakes in math doesn’t reliably move math forward for the population, and even for the individual only shows what they don’t know. | | |
| ▲ | paganel 4 hours ago | parent [-] | | I’m the OP, comparing all of human activity (like our day-to-day language, for example) with something like maths is a fallacy in itself. Second, maths itself isn’t “solved” by any means of imagination, up until 150-ish years ago we were still thinking that two parallel lines never intersecting was a pillar of our understaffing of the world, the same way as we now (still) take numbers for granted, for example. Yes, conquering the “low hills” of what we now regard as established science using AI can be quite enticing for some of us, but in so doing we lose sight of the much higher mountains that now sit behind those high hills. | | |
| ▲ | DonHopkins 4 hours ago | parent [-] | | If the world is as "understaffed" as you claim, delegating the menial work on the low hills to AI -- like proofreading your own post for example -- sounds like a reasonable way to free up some ambitious humans for climbing the mountains. |
|
|
|
|
|
|
| ▲ | snakeboy 7 hours ago | parent | prev | next [-] |
| > to bounce ideas off and catch any glaring errors These are two wildly different things. Microsoft Word's spell checker can catch glaring errors, but "bouncing ideas off" of an AI sounds more akin to passing your ideas through a "consensus sieve". |
|
| ▲ | duskdozer 5 hours ago | parent | prev | next [-] |
| >check for grammar and spelling mistakes. Non-chatbot spellcheckers have existed for ages and would easily flag anything of importance while not trying to ruin your own writing. |
|
| ▲ | hnarayanan 7 hours ago | parent | prev | next [-] |
| I found this particular typo quite funny. |
| |
| ▲ | DonHopkins 3 hours ago | parent [-] | | People who intentionally insert performative typos and misspellings and grammatical errors and nonsense words into their writing just to prove they're human should call themselves the "alt write". Maybe that explains the genius behind all those poorly spelled protest signs at MAGA rallies. |
|
|
| ▲ | AirMax98 7 hours ago | parent | prev | next [-] |
| > how hard is it to right 10 pages yourself Tough one. |
|
| ▲ | budman1 7 hours ago | parent | prev | next [-] |
| that spelling mistake was done on purpose, i expect. |
|
| ▲ | flohofwoe 6 hours ago | parent | prev | next [-] |
| Those little imperfections will become valuable signals in the future that the text has indeed not been touched by AI ;) ...of course it's easy to fake by instructing the LLM to place random spelling and grammar errors into the text, but this requires at least a minimal amount of thinking ahead by the human master ;) |
|
| ▲ | tjpnz 4 hours ago | parent | prev | next [-] |
| The last time I did this for a blog post I got a few grammatical fixes plus a gargantuan amount of crap on how to "soften" my tone. If I had followed all of its "advice" I would've been left with a bunch of words saying absolutely nothing. |
|
| ▲ | revolution88 7 hours ago | parent | prev | next [-] |
| Shame that he made a mistake? :) Better use AI and read slop? :) |
| |
| ▲ | pascahousut 7 hours ago | parent | next [-] | | I wish a healthy middle ground was an option. | |
| ▲ | novia 6 hours ago | parent | prev | next [-] | | Em seems likely to be short for Emily, yeah? | |
| ▲ | RobotToaster 7 hours ago | parent | prev [-] | | Grammar checkers have been around a long time before AI. (At least if you ignore that fuzzy logic used to be called "AI") |
|
|
| ▲ | dguest 7 hours ago | parent | prev [-] |
| [dead] |