{ "archive_path": "archive/1772869683.095627", "base_url": "lr0.org/blog/p/gpt", "basename": "", "bookmarked_date": "2026-03-07 07:48", "canonical": { "archive_org_path": "https://web.archive.org/web/lr0.org/blog/p/gpt", "dom_path": "output.html", "favicon_path": "favicon.ico", "git_path": "git/", "google_favicon_path": "https://www.google.com/s2/favicons?domain=lr0.org", "headers_path": "headers.json", "htmltotext_path": "htmltotext.txt", "index_path": "index.html", "media_path": "media/", "mercury_path": "mercury/content.html", "pdf_path": "output.pdf", "readability_path": "readability/content.html", "screenshot_path": "screenshot.png", "singlefile_path": "singlefile.html", "warc_path": "warc/", "wget_path": null }, "domain": "lr0.org", "downloaded_at": "2026-03-07T07:48:09.487816+00:00", "downloaded_datestr": "2026-03-07 07:48", "extension": "", "hash": "1FD14Z38AYKRA2SE77Q8", "history": { "archive_org": [ { "cmd": [ "/usr/bin/curl", "--silent", "--location", "--compressed", "--proxy", "socks5://tor-socks-proxy:9150", "--head", "--max-time", "60", "--user-agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 ArchiveBox/{VERSION} (+https://github.com/ArchiveBox/ArchiveBox/)", "https://web.archive.org/save/https://lr0.org/blog/p/gpt/" ], "cmd_version": "8.10.1", "end_ts": "2026-03-07T07:49:00.298267+00:00", "index_texts": null, "output": "https://web.archive.org/web/20260307074844/https://lr0.org/blog/p/gpt/", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:39.846466+00:00", "status": "succeeded" } ], "dom": [ { "cmd": [ "/usr/bin/chromium-browser", "--proxy-server=socks5://tor-socks-proxy:9150", "--disable-features=DarkMode", "--run-all-compositor-stages-before-draw", "--hide-scrollbars", "--autoplay-policy=no-user-gesture-required", "--no-first-run", "--use-fake-ui-for-media-stream", "--use-fake-device-for-media-stream", "--simulate-outdated-no-au='Tue, 31 Dec 2099 23:59:59 GMT'", "--headless=new", "--no-sandbox", "--no-zygote", "--disable-dev-shm-usage", "--disable-software-rasterizer", "--disable-sync", "--window-size=1440,2000", "--user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 ArchiveBox/{VERSION} (+https://github.com/ArchiveBox/ArchiveBox/)", "--user-data-dir=/data/personas/Default/chrome_profile", "--profile-directory=Default", "--dump-dom", "https://lr0.org/blog/p/gpt/" ], "cmd_version": "131.0.6778", "end_ts": "2026-03-07T07:48:24.114935+00:00", "index_texts": null, "output": "output.html", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:18.089571+00:00", "status": "succeeded" } ], "favicon": [ { "cmd": [ "/usr/bin/curl", "--silent", "--location", "--compressed", "--proxy", "socks5://tor-socks-proxy:9150", "--max-time", "60", "--output", "favicon.ico", "--user-agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 ArchiveBox/{VERSION} (+https://github.com/ArchiveBox/ArchiveBox/)", "https://www.google.com/s2/favicons?domain=lr0.org" ], "cmd_version": "8.10.1", "end_ts": "2026-03-07T07:48:13.033511+00:00", "index_texts": null, "output": "favicon.ico", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:09.912956+00:00", "status": "succeeded" } ], "git": [], "headers": [ { "cmd": [ "/usr/bin/curl", "--silent", "--location", "--compressed", "--proxy", "socks5://tor-socks-proxy:9150", "--head", "--max-time", "60", "--user-agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 ArchiveBox/{VERSION} (+https://github.com/ArchiveBox/ArchiveBox/)", "https://lr0.org/blog/p/gpt/" ], "cmd_version": "8.10.1", "end_ts": "2026-03-07T07:48:13.122839+00:00", "index_texts": null, "output": "headers.json", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:13.065940+00:00", "status": "succeeded" } ], "htmltotext": [ { "cmd": [ "(internal) archivebox.extractors.htmltotext", "./{singlefile,dom}.html" ], "cmd_version": "0.8.5rc51", "end_ts": "2026-03-07T07:48:35.147793+00:00", "index_texts": [ "(/favicon.svg) (/images/favicon.svg) (https://fonts.googleapis.com) (https://fonts.gstatic.com) (https://fonts.googleapis.com/css2?family=Amiri:ital,wght@0,400;0,700;1,400;1,700&family=Tinos:ital,wght@0,400;0,700;1,400;1,700&display=swap) I'm not consulting an LLM | La Vita Nouva (/styles/style.css) (/styles/blog.css) (https://cdn.jsdelivr.net/npm/katex@0.16.9/dist/katex.min.css) (/styles/responsive.css) (/) home \u2192 (/blog/) blog January 30, 2026 (Copy permalink) [permlink] I'm not consulting an LLM Here's my problem with using GPT, or an LLM generally for anything1 , even if the LLM would do it 'effectively', I will speak specifically of looking for information as an example, and let's assume the following scenario; ever used the \"I'm feeling Lucky\" button in Google? This button usually gives the first result of the search without actually showing you the search results, let's assume that, you lived in a perfect world where in every Google search you have ever done, you clicked this button, and it was extremely, extremely, precise and efficient in finding the perfect fit for whatever you were looking for, that is to say, every search you have ever done in your life, was successful, from the first hit. Now, in such a world, do you think that your intellect would has grown the same amount in which you had to actually do proper research, encounter crazy people, cultures, controversies, jokes, people who wrote interesting enough stuff that you followed them, arguments you disagreed with but couldn\u2019t quite dismiss, footnotes that led nowhere and everywhere at once, half-broken blogs, bad takes that forced you to sharpen your own, or sources that contradicted each other so hard you had to build a model of the world just to survive the tension? I guess not. Because what would be missing isn\u2019t information but the experience. And experience is where intellect actually gets trained. \u201cI\u2019m Feeling Lucky\u201d intelligence is optimized for arrival, not for becoming. You get the answer but nothing else (keep in mind we are assuming that it's a good answer ). You don\u2019t learn how ideas fight, mutate, or die. You don\u2019t develop a sense for epistemic smell or the ability to feel when something is off before you can formally prove it. Now back to reality, LLMs are never that good, they're never near that hypothetical \"I'm feeling lucky\", and this has to do with how they're fundamentally designed, I never so far asked GPT about something that I'm specialized at, and it gave me a sufficient answer that I would expect from someone who is as much as expert as me in that given field. People tend to think that GPT (and other LLMs) is doing so well, but only when it comes to things that they themselves do not understand that well (Gell-Mann Amnesia2 ), even when it sounds confident, it may be approximating, averaging, exaggerate (Peters 2025) or confidently (Sun 2025) reproducing a mistake. There is no guarantee whatsoever that the answer it gives is the best one, the contested one, or even a correct one, only that it is a plausible one. And that distinction matters, because intellect isn\u2019t built on plausibility but on understanding why something might be wrong, who disagrees with it, what assumptions are being smuggled in, and what breaks when those assumptions fail A tool can be efficient and still be intellectually corrosive, not because it lies all the time, but because it lies well enough. Its smoothness hides uncertainty, which is important unless you want intellect-rot. #(/blog/t/modus/) Modus Vivendi #LLMs Footnotes 1 Maybe I should add the exceptions of stupid tasks, i.e. repetitive and easily automatable procedures, things that I would make an Emacs macro for them before the age of LLMs. 2 \"Briefly stated, the Gell-Mann Amnesia effect is as follows. You open the newspaper to an article on some subject you know well. In Murray's case, physics. In mine, show business. You read the article and see the journalist has absolutely no understanding of either the facts or the issues. Often, the article is so wrong it actually presents the story backward\u2014reversing cause and effect. I call these the \"wet streets cause rain\" stories. Paper's full of them. In any case, you read with exasperation or amusement the multiple errors in a story, and then turn the page to national or international affairs, and read as if the rest of the newspaper was somehow more accurate about Palestine than the baloney you just read. You turn the page, and forget what you know.\" - Michael Crichton. References Peters, Uwe and Chin-Yee, Benjamin (2025). Generalization bias in large language model summarization\nof scientific research . The Royal Society. (http://dx.doi.org/10.1098/rsos.241776) Link Sun, Fengfei and Li, Ningke and Wang, Kailong and Goette,\nLorenz (2025). Large Language Models are overconfident and amplify human\nbias . arXiv. (https://arxiv.org/abs/2505.02151) Link Referenced in: (/blog/h/fv/) Favorites ; leads to: (/blog/t/modus/) Modus Vivendi (Artwork) This is an arbitrary picked image, hashed internally and mapped to this\npage. You will have to see it as long as you in my website. hash: b582cd88\u2026 \u2192 idx 24/132 Referenced in: (/blog/h/fv/) Favorites ; leads to: (/blog/t/modus/) Modus Vivendi \u00a9 2026 lr0 (/blog/h/rss/) (Subscribe via RSS) RSS \u00b7 (https://github.com/larrasket) Github \u00b7 (mailto:root@lr0.org) Contact Sine ira et studio Content freely available for educational use " ], "output": "htmltotext.txt", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:35.138008+00:00", "status": "succeeded" } ], "media": [ { "cmd": [ "/usr/local/bin/yt-dlp", "--restrict-filenames", "--trim-filenames", "128", "--write-description", "--write-info-json", "--write-annotations", "--write-thumbnail", "--no-call-home", "--write-sub", "--write-auto-subs", "--convert-subs=srt", "--yes-playlist", "--continue", "--no-abort-on-error", "--ignore-errors", "--geo-bypass", "--add-metadata", "--format=(bv*+ba/b)[filesize<=750m][filesize_approx<=?750m]/(bv*+ba/b)", "--skip-download", "--cache-dir=/data/yt-dlp-cache/", "--cookies=/data/yt-dlp-cache/cookies.txt", "--proxy=socks5://tor-socks-proxy:9150", "--no-playlist", "https://lr0.org/blog/p/gpt/" ], "cmd_version": "2024.10.7", "end_ts": "2026-03-07T07:48:39.819502+00:00", "index_texts": [], "output": "media/", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:36.317738+00:00", "status": "succeeded" } ], "mercury": [ { "cmd": [ "/home/archivebox/.npm/bin/postlight-parser", "https://lr0.org/blog/p/gpt/" ], "cmd_version": "2.2.3", "end_ts": "2026-03-07T07:48:35.108403+00:00", "index_texts": null, "output": "mercury/", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:33.391366+00:00", "status": "succeeded" } ], "pdf": [], "readability": [ { "cmd": [ "/home/archivebox/.npm/bin/readability-extractor", "/tmp/tmpf_o5d5_j", "https://lr0.org/blog/p/gpt/" ], "cmd_version": "0.0.11", "end_ts": "2026-03-07T07:48:26.718478+00:00", "index_texts": [ "home \u2192\nblogJanuary 30, 2026[permlink]I'm not consulting an LLMHere's my problem with using GPT, or an LLM generally for anything1, even if the LLM would do it 'effectively', I will speak specifically of looking for information as an example, and let's assume the following scenario; ever used the \"I'm feeling Lucky\" button in Google? This button usually gives the first result of the search without actually showing you the search results, let's assume that, you lived in a perfect world where in every Google search you have ever done, you clicked this button, and it was extremely, extremely, precise and efficient in finding the perfect fit for whatever you were looking for, that is to say, every search you have ever done in your life, was successful, from the first hit.Now, in such a world, do you think that your intellect would has grown the same amount in which you had to actually do proper research, encounter crazy people, cultures, controversies, jokes, people who wrote interesting enough stuff that you followed them, arguments you disagreed with but couldn\u2019t quite dismiss, footnotes that led nowhere and everywhere at once, half-broken blogs, bad takes that forced you to sharpen your own, or sources that contradicted each other so hard you had to build a model of the world just to survive the tension?I guess not.Because what would be missing isn\u2019t information but the experience. And experience is where intellect actually gets trained.\u201cI\u2019m Feeling Lucky\u201d intelligence is optimized for arrival, not for becoming. You get the answer but nothing else (keep in mind we are assuming that it's a good answer). You don\u2019t learn how ideas fight, mutate, or die. You don\u2019t develop a sense for epistemic smell or the ability to feel when something is off before you can formally prove it.Now back to reality, LLMs are never that good, they're never near that hypothetical \"I'm feeling lucky\", and this has to do with how they're fundamentally designed, I never so far asked GPT about something that I'm specialized at, and it gave me a sufficient answer that I would expect from someone who is as much as expert as me in that given field. People tend to think that GPT (and other LLMs) is doing so well, but only when it comes to things that they themselves do not understand that well (Gell-Mann Amnesia2), even when it sounds confident, it may be approximating, averaging, exaggerate (Peters 2025) or confidently (Sun 2025) reproducing a mistake. There is no guarantee whatsoever that the answer it gives is the best one, the contested one, or even a correct one, only that it is a plausible one. And that distinction matters, because intellect isn\u2019t built on plausibility but on understanding why something might be wrong, who disagrees with it, what assumptions are being smuggled in, and what breaks when those assumptions failA tool can be efficient and still be intellectually corrosive, not because it lies all the time, but because it lies well enough. Its smoothness hides uncertainty, which is important unless you want intellect-rot. #Modus Vivendi #LLMsFootnotesReferencesPeters, Uwe and Chin-Yee, Benjamin (2025). Generalization bias in large language model summarization\nof scientific research. The Royal Society. LinkSun, Fengfei and Li, Ningke and Wang, Kailong and Goette,\nLorenz (2025). Large Language Models are overconfident and amplify human\nbias. arXiv. LinkThis is an arbitrary picked image, hashed internally and mapped to this\npage. You will have to see it as long as you in my website. hash: b582cd88\u2026 \u2192 idx 24/132" ], "output": "readability/", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:25.233205+00:00", "status": "succeeded" } ], "screenshot": [], "singlefile": [], "title": [ { "cmd": [ "/usr/bin/curl", "--silent", "--location", "--compressed", "--proxy", "socks5://tor-socks-proxy:9150", "--max-time", "60", "--user-agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 ArchiveBox/{VERSION} (+https://github.com/ArchiveBox/ArchiveBox/)", "https://lr0.org/blog/p/gpt/" ], "cmd_version": "8.10.1", "end_ts": "2026-03-07T07:48:24.302331+00:00", "index_texts": null, "output": "I'm not consulting an LLM | La Vita Nouva", "pwd": "/data/archive/1772869683.095627", "schema": "ArchiveResult", "start_ts": "2026-03-07T07:48:24.262528+00:00", "status": "succeeded" } ], "wget": [] }, "icons": null, "is_archived": true, "is_static": false, "latest": { "archive_org": "https://web.archive.org/web/20260307074844/https://lr0.org/blog/p/gpt/", "dom": "output.html", "favicon": "favicon.ico", "git": null, "media": "media/", "pdf": null, "screenshot": null, "singlefile": null, "title": "I'm not consulting an LLM | La Vita Nouva", "warc": null, "wget": null }, "link_dir": "/data/archive/1772869683.095627", "newest_archive_date": "2026-03-07T07:48:39.846466+00:00", "num_failures": 0, "num_outputs": 9, "oldest_archive_date": "2026-03-07T07:48:09.912956+00:00", "path": "/blog/p/gpt/", "schema": "Link", "scheme": "https", "snapshot_abid": "snp_01KK3M928H1CC80E2B01RAKSMA", "snapshot_id": "e638d3f9-afc4-48a9-95fb-f44970a9e68a", "sources": [ "/data/sources/1772869682-import.txt" ], "tags": null, "tags_str": "", "timestamp": "1772869683.095627", "title": "I'm not consulting an LLM | La Vita Nouva", "url": "https://lr0.org/blog/p/gpt/" }