| ▲ | snowmobile 7 hours ago |
| > That 20ms is a smoking gun - it lines up perfectly with the mysterious pattern we saw earlier! Speaking of smoking guns, anybody else reckon Claude overuses that term a lot? Seems anytime I give it some debugging question, it'll claim some random thing like a version number or whatever, is a "smoking gun" |
|
| ▲ | eieio 6 hours ago | parent | next [-] |
| Yes! While this post was written entirely by me, I wouldn't be surprised if I had "smoking gun" ready to go because I spent so much time debugging with Claude last night. |
| |
| ▲ | jabwd 39 minutes ago | parent | next [-] | | Serious question though, since AI seems to be so all capable and intelligent. Why wouldn't it be able to tell you the exact reason that I could tell you just by reading the title of this post on HN? It is failing even at the one thing it could probably do decently, is being a search engine. | |
| ▲ | rubslopes 5 hours ago | parent | prev | next [-] | | It's interesting how LLMs influence us, right? The opposite happened to me: I loved using em dashes, but AI ruined it for me. | | | |
| ▲ | gf000 6 hours ago | parent | prev [-] | | Reminds me of ethimology nerd's videos. He has some content about how LLMs will influence human language. | | |
| ▲ | hinkley 6 hours ago | parent | next [-] | | Some day in the future we will complain about AIs with a 2015 accent because that’s the last training data that wasn’t recursive. | |
| ▲ | grim_io 6 hours ago | parent | prev | next [-] | | The "maybe" of yesterday is the "you're absolutely right!" of tomorrow. | |
| ▲ | ranger_danger 6 hours ago | parent | prev [-] | | shouldn't it be "human language influences human language"? |
|
|
|
| ▲ | yread 6 hours ago | parent | prev | next [-] |
| ChatGPT too. And "lines up perfectly" when it doesnt actually line up with anything |
| |
| ▲ | dave78 6 hours ago | parent | next [-] | | Same with Gemini. | | |
| ▲ | MonkeyClub 5 hours ago | parent [-] | | You can absolutely see this pattern in Gemini in 2026. Btw, is the injection of "absolutely" and "in $YEAR" prevalent in other LLMs as well, or is it just in Gemini's dialect? | | |
| ▲ | cristoperb 5 hours ago | parent [-] | | It's just Gemini. I'm guessing they changes the system prompt for the new year or something, but it's pretty annoying. |
|
| |
| ▲ | redwall_hp 6 hours ago | parent | prev | next [-] | | "You're so right, that nice catch lines up perfectly!" | | |
| ▲ | smallmancontrov 6 hours ago | parent | next [-] | | It's not just a coincidence, it's the emergence of spurious statistical correlations when observations happen across sessions rather than within sessions. | |
| ▲ | f1shy 6 hours ago | parent | prev [-] | | You can add an M-dash, and we completed the bs-bingo. :) |
| |
| ▲ | locallost 6 hours ago | parent | prev [-] | | I chuckled out loud. It's funny cause it's true. |
|
|
| ▲ | observationist 5 hours ago | parent | prev | next [-] |
| Or the "Eureka! That's not just a smoking gun, it's a classic case of LLMspeak." Grok, ChatGPT, and Claude all have these tics, and even the pro versions will use their signature phrases multiple times in an answer. I have to wonder if it's deliberate, to make detecting AI easier? |
| |
| ▲ | WesolyKubeczek 5 hours ago | parent [-] | | A computational necromancer has likely figured out a way to power a data center by making Archimedes spin in his grave very fast. |
|
|
| ▲ | jcims 5 hours ago | parent | prev | next [-] |
| I'm working on a little SRE agent to pre-load tickets with information to help our on-call and I'm already tired of Claude finding 'smoking guns'. |
|
| ▲ | Telemakhos 6 hours ago | parent | prev | next [-] |
| I've love to delve into that. https://pshapira.net/2024/03/31/delving-into-delve/ |
|
| ▲ | bdamm 6 hours ago | parent | prev | next [-] |
| Without knowing how LLM's personality tuning works, I'd just hazard a guess that the excitability (tendency to use excided phrases) is turned up. "smoking gun" must be highly rated as a term of excitability. This should apply to other phrases like "outstanding!" or "good find!" "You're right!" etc. |
|
| ▲ | HPsquared 5 hours ago | parent | prev | next [-] |
| They love clichés, and hate repeating the same words for something (repetition penalty) so they'll say something like "cause" then it's a "smoking gun" then it's something else |
|
| ▲ | jcynix 6 hours ago | parent | prev | next [-] |
| You might see certain phrases and mdashes ;-) rather often, because … these programs are trained on data written by people (or Microsoft's spelling correction) which overused them in the last n years? So what should these poor LLMs generate instead? |
|
| ▲ | cipehr 6 hours ago | parent | prev | next [-] |
| I don't think claude has even once used this in my conversations (Claude Desktop, Claude Code, Voice conversations...) Sycophancy, yes absolutely! Maybe it has something to do with your profile/memories? |
|
| ▲ | layer8 5 hours ago | parent | prev | next [-] |
| Yes, it’s kind of a corpus delicti. ;) |
|
| ▲ | lloydatkinson 7 hours ago | parent | prev | next [-] |
| smoking gun, you're absolutely right, good question, em dash, "it isn't just foo, it's also bar", real honest truth, brutal truth, underscores the issue, delves into, more em dashes, <20 different hr/corporate/cringe phrases>. It's nauseating. |
| |
| ▲ | jcynix 6 hours ago | parent | next [-] | | It's what they read on The Internets when training, so don't expect them to generate new phrases, other than what they learned from it? | | |
| ▲ | MaxBarraclough 4 hours ago | parent | next [-] | | That's the point though, it doesn't reflect human usage of the word. If
delve were so commonly used by humans too, we wouldn't be discussing
how it's overused by LLMs. | |
| ▲ | Terretta 6 hours ago | parent | prev [-] | | ### The answer that fits everything (and what to do about it) | | |
| ▲ | jcynix 5 hours ago | parent | next [-] | | Maybe we need a real AI which creates new phrases and teaches the poor LLMs? Looking back we already had similar problems, when we had to ask our colleagues, students, whomever "Did you get your proposed solution from the answers part or the questions part of a stackoverflow article?" :-0 | |
| ▲ | calvinmorrison 5 hours ago | parent | prev [-] | | cant wait for chatgpt to make me read about grandmas secret recipe and scroll through 6 ads to see the ingredients for my chicken teriyaki dinner |
|
| |
| ▲ | hamdingers 5 hours ago | parent | prev | next [-] | | You might find this a fun read: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing | |
| ▲ | cubano 6 hours ago | parent | prev [-] | | Come on...haven't we all had to deal with the crazy smart lead who was loaded with those same types of annoying tics? Considering what these LLMs bring to the table, I think a little tolerance for their cringe phrases is in order. |
|
|
| ▲ | nurettin 5 hours ago | parent | prev | next [-] |
| At this I'm just so glad that "you're absolutely right!" phase is over. |
|
| ▲ | simonjgreen 6 hours ago | parent | prev | next [-] |
| I see it from GPT5 too a lot |
|
| ▲ | Hikikomori 7 hours ago | parent | prev | next [-] |
| It's a smoking gun of Claude usage. |
|
| ▲ | Fnoord 6 hours ago | parent | prev | next [-] |
| > Speaking of smoking guns Oh shoot! A shooting. So the TL;DR of this post is: don't change this setting unless you know what you're doing. |
|
| ▲ | kevin_thibedeau 6 hours ago | parent | prev [-] |
| Chastise it with a reminder that you're using smokeless powder. |
