A City on Mars by Zach Weinersmith goes over a lot of these points and many others, like politics and laws of space. Like the title of this article, the tldr is "life in space would suck".
I had a fun result the other day from Claude. I opened a script in Zed and asked it to "fix the error on line 71".
Claude happily went and fixed the error on line 91....
1. There was no error on line 91, it did some inconsequential formatting on that line
2. More importantly, it just ignored the very specific line I told it to go to. It's like I was playing telephone with the LLM which felt so strange with text-based communication.
This was me trying to get better at using the LLM while coding and seeing if I could "one-shot" some very simple things. Of course me doing this _very_ tiny fix myself would have been faster. Just felt weird and reinforces this idea that the LLM isn't actually thinking at all.
I suspect if OP highlighted line 71 and added it to chat and said fix the error, they’d get a much better response. I assume Cursor could create a tool to help it interpret line numbers, but that’s not how they expect you to use it really.
That's the thing. We're expecting the tool to have a clear understanding of its own limitations by now and ask for better prompts (or say: I don't know, I can't etc). The fact it just does something wacky is not good at all to the consistency of these tools.
I do not code/program, but I do read thousands of fiction pages annually. LLMs (Perplexity, specifically) have been my lifetime favorite book club member — I can ask anything.
However, I can't just say "on page 123..." I've found it's better to either provide the quote, or describe the context, and then ask how it relates to [another concept]. Or I'll say "at the end of chapter 6, Bob does X, then why Y?" (perhaps this is similar to asking a coding LLM to fix a specific function instead of a specific line?).
My favorite examples of this have been sitting with living human authors and discussing their books — usually to jaw-dropped creators, particularly to Unknowns.
Works for non-fiction, too (of course). But for all those books you didn't read in HS English classes, you can somewhat recreate all that class discussion your teachers always attempted to foster — at your own discretion/direction.
> This was me trying to get better at using the LLM while coding
And now you've learned that LLMs can't count lines. Next time, try asking it to "fix the error in function XYZ" or copy/paste the line in question, and see if you get better results.
> reinforces this idea that the LLM isn't actually thinking at all.
Of course it's not thinking, how could it? It's just a (rather big) equation.
54 def dicts_to_table_string(
55 headings: List[str], dicts: List[Dict[str, str]]
56 ) -> List[str]:
57 max_lengths = [len(h) for h in headings]
58
59 # Compute maximum length for each column
60 for d in dicts:
That’s not what he’s saying there. There’s a separate tool that adds line numbers before feeding the prompt into the LLM. It’s not the LLM doing it itself.
It's a tool. It's not a human. A line number works great for humans. Today, they're terrible for LLMs.
I can choose to use a screwdriver to hammer in a nail and complain about how useless screwdrivers are. Or I can realize when and how to use it.
We (including marketing & execs) have made a huge mistake in anthropomorphizing these things, because then we stop treating them like tools that have specific use cases to be used in certain ways, and more like smart humans that don't need that.
Maybe one day they'll be there, but today they are screwdrivers. That doesn't make them useless.
Check the whole ecosystem around editors, grep tools, debuggers, linting and build tools. One common thing about all of this is line (and column) number so you can integrate them together if you want to automate stuff. Like jumping to errors (quickfix in vim,…), search all files and jump to the occurrences (grep mode in emacs,…), etc…
> I’m less empathetic than I might be because I came into the office 5 days a week for 30 years. My wife also worked. We raised three kids. I went to night school. It’s all very doable, and honestly not that hard.
To me this sentiment reads as "It sucked for me, therefore it needs to suck for you too. Feel the pain of previous generations!"
What happened to wanting to make life BETTER for people? Better for the next generation?
As someone that would complain about RTO mandates if I had to, I know that it's do-able, but does it make my life better? No, it doesn't.
Imagine your last 30 years of not having to go in 5 days a week? Think how much more time you would have had to do all the things you listed: raise your kids, spend time studying night school, etc. How much further ahead would you have gotten with that extra time?
The first thing that stuck out to me (emphasis added):
>> When I plead with my direct reports to please comply with the company policy of in the office 3 days a week
Someone higher up is the decision maker here. They are acknowledging a lack of empathy while implementing those policies and trying to explain why they may lack empathy in the process. Yet, at the end of the day, they are simply one of the people who has to ensure compliance.
> Imagine your last 30 years of not having to go in 5 days a week?
There are likely a lot of managers out there arguing against company mandates. The thing is, it is difficult to discuss their struggles with higher levels of management without creating a negative impact (or a negative impact of a different sort) in the workplace. So they have to carry out the orders without actually discussing how they feel about those orders with their reports.
Canada uses the verb "to table" to mean to place on the agenda, which is the opposite of how it's used in the US, where it means to remove from consideration indefinitely.
Imagine meetings during WW2 with American and British generals, where the Americans proposed an urgent plan, and to which the British enthusiastically responded "Let's table that immediately!"
Interestingly, the UK/US language divide directly led to consequences in the Korean War. When a British general understated the severity of conditions faced by UK troops, an American general took the words at face value and did not provide reinforcements or told him to withdraw. That led to a last stand, where only a tiny fraction of British troops were able to escape. From The Guardian [1]:
"[W]hen the British brigadier reported the position to his American superior in the United Nations joint command, he did so with classic and — as it turned out — lethal British understatement.
""Things are a bit sticky, sir," Brig Tom Brodie of the Gloucestershire Regiment told General Robert H Soule, intending to convey that they were in extreme difficulty.
"But Gen Soule understood this to mean "We're having a bit of rough and tumble but we're holding the line". Oh good, the general decided, no need to reinforce or withdraw them, not yet anyway. [...]
"The programme says: "Any hopes of relief were dashed by an American misunderstanding of British understatement.""
As a non native speaker of English, I have a hard time putting an equal sign between "Things are a bit sticky" and "[we are] in extreme difficulty"
Are these sentences really similar to a British English speaker?
To me the first one means "we have some minor issues" if talked literally, or "we have bigger issues but I decided to add a layer of nonchalance so that you miss the point"
In most contexts, you are correct that the translation of "Things are a bit sticky" is typically not interpreted as "We are in extreme difficulty."
However, in that specific case, the British general supposed that it was the point of pride for a British officer to rarely admit a weakness or lack of control over a situation. So, the slightest admission of the circumstances being "a bit sticky" should have been a sign that circumstances were severe, or otherwise he would have avoided making any admission at all.
The less ambiguous way—which would have avoided any ambiguity due to the general's understatement—would have been for him to state the facts: his troops were substantially outnumbered, and therefore they could only realistically last a short amount of time without support or withdrawal. However, perhaps, it is possible that he could not send a message of that length in the circumstances of the time.
---
I took a brief look at your profile to try and guess your native language to make a comparison, and it appears you may be a francophone.
A perhaps similar example would be if you ask someone « Ça va ? » ("How goes it?") and the other person responds by saying: « Ça va... » ("It goes..."). For some people, « Ça va » is their default response, so it means that their situation is no different than usual. For others, who you might know to usually say the chipper response « Bien ! Et toi ? », a sudden change to « Ça va... » may be a hint that things aren't going so well, and a way to avoid directly saying « Non, rien ne va et je suis déprimé » (as taken from [1]).
The British general's phrase therefore had a distinct literal meaning, but he meant for the phrase to carry a different message that he expected the US general to pick up on (which did not happen, as the US general interpreted the phrase by its literal meaning instead).
As for "ça va": if I had a tumor dangling from my leg and went to the doctor, I could answer when asked "comment ça va?"
- "ça vaaaaaaa...." because I am a Real Man (TM) who does not show weakness, but I should suck it up and cut the tumor myself instead of coming and whining. And only hope that the MD would probe me until I talked about the "sticky thing" that weights 15 kg and makes me turn right when I walk. I should not have come to the MD at all
- or say what I have because I came for that.
By their logic, I do not understand why the British admitted to any problems, putting their honor in jeopardy for the small reward of maybe having their lives saved (and the lives of the people under the general who maybe had a different view on their future).
The definition of tabled used is "next on the agenda" (aka definition 1b instead of 1a for the verb at Merriam Webster [1]).
Generally, articles about Canada, the United Kingdom, and other Commonwealth countries use the 1b definition, whereas articles about the United States typically use the 1a definition. I can't recall any article about Canadian news in particular, which uses the 1a definition for "tabled."
I think OP was being sarcastic. I think that because they added TM (for trademark) after "Feature", which I take to mean sarcasm is being expressed in the sentence.
All that to say, myself (and likely OP) agree with your thoughts.
This sent me down a good rabbit hole. Ended up finding a simpler userChrome.css that removed the native tabs. I'm sure yours does a lot more cleaning up of the UI but the following worked well for me: https://github.com/taylorsilva/dotfiles#hide-firefoxs-native...
