{
    "archive_path": "archive/1792879566.162145",
    "base_url": "www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom",
    "basename": "anthropic-claude-citrini-vibecoding-scorpion-antivenom",
    "bookmarked_date": "2026-10-24 22:06",
    "canonical": {
        "archive_org_path": "https://web.archive.org/web/www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom",
        "dom_path": "output.html",
        "favicon_path": "favicon.ico",
        "git_path": "git/",
        "google_favicon_path": "https://www.google.com/s2/favicons?domain=www.theverge.com",
        "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": "www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom.html"
    },
    "domain": "www.theverge.com",
    "extension": "",
    "hash": "GTK3SRBGRCXZ021ZG190",
    "history": {
        "archive_org": [],
        "dom": [],
        "favicon": [
            {
                "cmd": [
                    "curl",
                    "--silent",
                    "--location",
                    "--compressed",
                    "--max-time",
                    "120",
                    "--output",
                    "favicon.ico",
                    "--user-agent",
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) curl/curl 8.14.1 (x86_64-pc-linux-gnu)",
                    "https://www.google.com/s2/favicons?domain=www.theverge.com"
                ],
                "cmd_version": "curl 8.14.1 (x86_64-pc-linux-gnu)",
                "end_ts": "2026-10-24T22:06:47.495689+00:00",
                "index_texts": null,
                "output": "favicon.ico",
                "pwd": "/data/archive/1792879566.162145",
                "schema": "ArchiveResult",
                "start_ts": "2026-10-24T22:06:46.764824+00:00",
                "status": "succeeded"
            }
        ],
        "git": [],
        "headers": [
            {
                "cmd": [
                    "curl",
                    "--silent",
                    "--location",
                    "--compressed",
                    "--head",
                    "--max-time",
                    "120",
                    "--user-agent",
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) curl/curl 8.14.1 (x86_64-pc-linux-gnu)",
                    "https://www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom"
                ],
                "cmd_version": "curl 8.14.1 (x86_64-pc-linux-gnu)",
                "end_ts": "2026-10-24T22:06:47.770782+00:00",
                "index_texts": null,
                "output": "headers.json",
                "pwd": "/data/archive/1792879566.162145",
                "schema": "ArchiveResult",
                "start_ts": "2026-10-24T22:06:47.506171+00:00",
                "status": "succeeded"
            }
        ],
        "htmltotext": [],
        "media": [],
        "mercury": [
            {
                "cmd": [
                    "/app/node_modules/@postlight/parser/cli.js",
                    "https://www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom"
                ],
                "cmd_version": "1.0.0",
                "end_ts": "2026-10-24T22:07:41.571900+00:00",
                "index_texts": null,
                "output": "mercury",
                "pwd": "/data/archive/1792879566.162145",
                "schema": "ArchiveResult",
                "start_ts": "2026-10-24T22:07:36.802005+00:00",
                "status": "succeeded"
            }
        ],
        "pdf": [],
        "readability": [
            {
                "cmd": [
                    "/app/node_modules/readability-extractor/readability-extractor",
                    "/tmp/tmpg9cqc6gt",
                    "https://www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom"
                ],
                "cmd_version": "0.0.11",
                "end_ts": "2026-10-24T22:07:36.792281+00:00",
                "index_texts": [
                    "An investment research firm wanted to prove AI could revolutionize drug development. So they teamed up with Anthropic to see whether an unreleased version of Claude could make scorpion antivenom. It couldn\u2019t. It came up with some promising starting points, but nothing close to an actual drug, experts tell The Verge.Citrini Research, the firm behind the experiment, admitted that \u201cnone of us could claim to know anything about AI as it related to biology.\u201d That didn\u2019t stop it from trying to make a drug from scratch \u2014 or publishing a blog post titled \u201cWe Wanted to Use Claude to Create a New Drug. Here\u2019s What Happened.\u201d The account came complete with rhetorical questions like \u201cWhy don\u2019t we try to use AI to create a new drug?\u201d, a blow-by-blow account of its amateurish scientific adventures, and a quote from Charles Darwin.If the name Citrini sounds familiar, that\u2019s because the firm was behind a widely circulated piece of fiction imagining an AI-induced economic catastrophe that gained traction on social media and rattled real-world markets. It also claims to have visited the Strait of Hormuz in April to get a firsthand perspective on what was happening in the volatile region.For its latest venture, Citrini enlisted the help of Anthropic, which, mere weeks out from its hotly anticipated IPO, has a few reasons to talk up AI\u2019s potential in drug development and the life sciences \u2014 two areas it\u2019s actively pursuing.The collaboration came about after Citrini ran into Claude\u2019s biosecurity guardrails while trying to get the model to research drug candidates. The post\u2019s author said they \u201cspam called anyone in my contact list who worked at an AI lab,\u201d eventually finding a willing partner in Anthropic. The AI lab agreed to drop the restrictions and give the team access to a more advanced, unreleased model on the condition that they work from its offices. \u201cLuckily,\u201d Anthropic also agreed to foot the hefty compute and token bill, which came just shy of $50,000.After weighing a few options, the team settled on scorpion antivenom, a costly treatment that can be difficult to produce, often involving injecting venom into horses. The goal was to use Claude to design proteins that could bind to the toxins in scorpion venom. Armed with a 35-page prompt, they set the AI to work, unleashing some 300 subagents to discover suitable proteins.In its own more sober account of the experiment, Anthropic said Claude generated nearly 320,000 candidates, whittling them down to 180 designs after discarding those that resembled known toxins or existing proteins. The entire process took 64 hours. Anthropic said the team worked \u201cwith Claude\u201d to add another 31 designs, bringing the total to 211.Citrini then sent the designs to two outside laboratories \u2014 Swiss biotech company Adaptyv Bio and US-based Twist Biosciences \u2014 to test whether the proteins could actually bind to their intended targets, a key step for developing an effective antivenom. That cost another $150,000, give or take. It\u2019s unclear why Anthropic could not have conducted these tests in-house at its biology wet lab in California. Seventeen of the proteins passed muster, collectively binding to four of the five scorpion toxins the team had hoped to target. Not one of the proteins bound to more than a single toxin, Citrini said.Even if they had, Citrini would still be a very long way from a working antivenom. Binding to a toxin does not mean a protein can actually neutralize it, let alone function as a safe and effective treatment. Citrini acknowledges this itself, noting that \u201cno experiment has yet tested whether they actually stopped the toxin working.\u201dIn other words, the experiment had not succeeded. Citrini set out to make a new drug, but experts tell The Verge it had only accomplished the relatively \u201ceasy\u201d part of the process. \u201cIt is easy-ish to discover a good binder against snake and scorpion toxins,\u201d said Andreas Hougaard Laustsen-Kiel, a professor of antibody technologies at the Technical University of Denmark. \u201cThe hard part is to translate it into a medicine.\u201dMelisa Benard Valle, an assistant professor, and Anne Ljungars, a senior researcher, both at the Technical University of Denmark, agreed. \u201cThe results are technically promising, but some of the excitement is premature,\u201d they wrote in a joint email, describing the findings as \u201cfar from a medicine and hyped.\u201d Much remains unknown about the proteins Claude designed, they said, including their safety, stability, how they behave in the body, and whether they can be developed into viable treatments. \u201cTranslating these binders into an actual medicine is likely still a long and challenging process.\u201dThe most novel aspect of Citrini\u2019s experiment, they said, was the \u201cautonomous discovery process rather than the biological results.\u201d AI has huge potential to accelerate discovery, they added, but warned \u201cturning promising molecules into effective medicines remains a much greater challenge.\u201dNor is the underlying approach particularly new. Andreas Bender, a professor of machine learning in medicine at Khalifa University in Abu Dhabi, told The Verge existing methods like high-throughput screening \u201care often able to find a multitude of hits at manageable cost,\u201d even without any AI. Designing proteins that bind to targets is \u201ckind of\u201d a solved problem, said Bender, who is also a visiting professor at the University of Cambridge. The much harder challenge is turning those results into treatments that actually work in living systems. \u201cIt\u2019s exactly this translation that lacks.\u201dWhile it failed to make a drug, Citrini declared the experiment a success of sorts. The firm argued it offers a glimpse into the investment opportunities emerging in the upcoming era of AI-enabled drug discovery. As for why it didn\u2019t bother to take the research further? Citrini accused critics of \u201cnitpick[ing]\u201d and added, \u201cNot to beat a dead horse, but we are an investment research firm - not a biotech startup.\u201d Citrini and Anthropic did not respond to requests for comment.But it still made a bullish case for companies that might benefit. Naturally, the specifics were reserved for paying subscribers, though Bloomberg reports the firm highlighted companies involved in the testing side of drug development, including Charles River Laboratories, which supplies primates for animal research. In a video discussing the experiment, Citrini described the AI portion as \u201cfree,\u201d conveniently overlooking the tab picked up by Anthropic.Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.Robert Hart"
                ],
                "output": "readability",
                "pwd": "/data/archive/1792879566.162145",
                "schema": "ArchiveResult",
                "start_ts": "2026-10-24T22:07:33.746408+00:00",
                "status": "succeeded"
            }
        ],
        "screenshot": [],
        "singlefile": [],
        "title": [
            {
                "cmd": [
                    "curl",
                    "--silent",
                    "--location",
                    "--compressed",
                    "--max-time",
                    "120",
                    "--user-agent",
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) curl/curl 8.14.1 (x86_64-pc-linux-gnu)",
                    "https://www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom"
                ],
                "cmd_version": "curl 8.14.1 (x86_64-pc-linux-gnu)",
                "end_ts": "2026-10-24T22:07:33.736181+00:00",
                "index_texts": null,
                "output": "Claude did not invent scorpion antivenom | The Verge",
                "pwd": "/data/archive/1792879566.162145",
                "schema": "ArchiveResult",
                "start_ts": "2026-10-24T22:07:33.656283+00:00",
                "status": "succeeded"
            }
        ],
        "wget": [
            {
                "cmd": [
                    "wget",
                    "--no-verbose",
                    "--adjust-extension",
                    "--convert-links",
                    "--force-directories",
                    "--span-hosts",
                    "--no-parent",
                    "-e",
                    "robots=off",
                    "--reject=js,mjs,woff,woff2,ttf,otf,eot,mp4,m4v,mov,webm,ogv,mkv,avi,flv",
                    "--timeout=120",
                    "--restrict-file-names=windows",
                    "--page-requisites",
                    "--user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 ArchiveBox/0.7.4 (+https://github.com/ArchiveBox/ArchiveBox/) wget/GNU Wget 1.21.3",
                    "--compression=auto",
                    "--timestamping",
                    "https://www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom"
                ],
                "cmd_version": "GNU Wget 1.21.3",
                "end_ts": "2026-10-24T22:07:33.646922+00:00",
                "index_texts": null,
                "output": "www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom.html",
                "pwd": "/data/archive/1792879566.162145",
                "schema": "ArchiveResult",
                "start_ts": "2026-10-24T22:06:47.781423+00:00",
                "status": "succeeded"
            }
        ]
    },
    "icons": null,
    "is_archived": true,
    "is_static": false,
    "latest": {
        "archive_org": null,
        "dom": null,
        "favicon": "favicon.ico",
        "git": null,
        "media": null,
        "pdf": null,
        "screenshot": null,
        "singlefile": null,
        "title": "Claude did not invent scorpion antivenom | The Verge",
        "warc": null,
        "wget": "www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom.html"
    },
    "link_dir": "/data/archive/1792879566.162145",
    "newest_archive_date": "2026-10-24T22:07:36.802005+00:00",
    "num_failures": 0,
    "num_outputs": 6,
    "oldest_archive_date": "2026-10-24T22:06:46.764824+00:00",
    "path": "/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom",
    "schema": "Link",
    "scheme": "https",
    "snapshot_id": "41898809-8676-4dbb-9b45-18696d2f4b26",
    "sources": [
        "/data/sources/1792879566-import.txt"
    ],
    "tags": null,
    "tags_str": "",
    "timestamp": "1792879566.162145",
    "title": "Claude did not invent scorpion antivenom | The Verge",
    "updated": "2026-10-24T22:06:46.762513+00:00",
    "updated_date": "2026-10-24 22:06",
    "url": "https://www.theverge.com/ai-artificial-intelligence/1016443/anthropic-claude-citrini-vibecoding-scorpion-antivenom"
}