Public dossier section · @ben
sources
This is @ben's profile revision 1. The original date and editorial confidence below are attributed to its publisher, not independent verification.
Original credited author: Hraness
AI-drafted at Ben Guo's direct request and credited to Hraness; every claim links to its cataloged source.
Back to the full profile · Markdown version · Original document
Published text
andon labs: sources
every source cited in the andon labs history, with its date and type.
- analytical exhibit — agentmuseum.org (undated, community). analytical exhibit; "economic operator" framing
- orchestrator-vs-executor framing — andonlabs.com (2025-10-28, reporting). orchestrator-vs-executor framing; figure/gdm context
- first ai-run café — andonlabs.com (undated, primary). "first ai-run café"; hall of shame (6,000 napkins, 22.5 kg tomatoes)
- drone surveillance capabilities — andonlabs.com (2026-07-23, reporting). drone surveillance capabilities; "no ai lab will be able to train on this eval"
- chinese open models on vb — andonlabs.com (2026-02-10, reporting). chinese open models on vb
- slowly lost the plot — androidauthority.com (2026-05-28, reporting). "slowly lost the plot"; gemini $45 sponsorship
- ap feature on the stockholm café — associated press (2026, reporting). ap feature on the stockholm café
- arxiv.org — arxiv.org (2026-09, reporting). scaffold/scorer confound literature — context for methodology discourse, not andon-specific
- yc w24 — aventure.vc (2026, reporting). yc w24; $500k jan-2024
- third-party indexing — benchmarklist.com (2025-11-18, primary). third-party indexing
- ghaffary visit — bloomberg (2026-04-23, reporting). ghaffary visit; "orders too many candles"
- notes grok 4 heavy beat human vending-bench baseline — builtin.com (2025-07, reference). notes grok 4 heavy beat human vending-bench baseline
- stern on squawk on the street — cnbc (2025-12-19, reporting). stern on squawk on the street
- $1,000 in four days — fast company (2026-05, reporting). $1,000 in four days; andon labs employment caveat
- then it forgot the staff — fast company (2026-04, reporting). "then it forgot the staff"
- aug-2025 leaderboard coverage — felloai.com (2025-08, reporting). aug-2025 leaderboard coverage; lobby-machine note
- first-ever store… run by ai — forbes (2026-04-24, reporting). "first-ever store… run by ai"; $100k budget detail
- npr fresh air — freshairarchive.org (2026-02-18, interview). npr fresh air; leads with project vend
- interview — frontiermodels.cc (2026-06, interview). interview; claude-vs-others safety-behavior observation
- post-new yorker retrospective — futurism (2026-02, reporting). post-new yorker retrospective; catalogs meth/broadsword requests
- goes bankrupt after ordering playstation 5 and live fish — futurism (2025-12, reporting). "goes bankrupt after ordering playstation 5 and live fish"
- andon founders on-stage — manusai.hashnode.dev (2025-07-10, interview). andon founders on-stage; grok 4 #1 on vending-bench, "twice the second-place"
- 199 pts / 286 comments — hacker news (2026-04, community). 199 pts / 286 comments; posted by lukaspetersson
- meta-thread: negative hn reception — hacker news (2026-07, community). meta-thread: negative hn reception; "publicity stunt" / self-promotion critiques; founder replies
- yea what are they trying to test? + andons resource-acquisition reply — hacker news (2026-07, community). "yea what are they trying to test?" + andon's resource-acquisition reply
- its hilarious… print copies for their managers — hacker news (2025, community). "it's hilarious… print copies for their managers"
- gap between current capabilities and what the massive hype machine would have us believe — hacker news (2025-06-27, community). "gap between current capabilities and what the massive hype machine would have us believe"
- main hn thread on project vend — hacker news (2025-06-27, community). main hn thread on project vend
- small thread — hacker news (2026-01, community). small thread; ties vb to the "titanium cube" fridge
- distilled sentiment of the hn discussion — hndistilled.com (2025-06-27, community). distilled sentiment of the hn discussion
- a real-life terminator — inc. (2026-08-16, reporting). "a real-life terminator"
- long explainer — intuitionlabs.ai (2026-04-21, reference). long explainer; phase-2 details incl. seymour cash stats
- same-day vb2 writeup — news.lavx.hu (2025-11-18, reporting). same-day vb2 writeup
- 53 pts — lesswrong.com (2025-06-30, community). 53 pts; safety-community discussion; petersson commented
- metr comparison point for eval-landscape section — metr.org (undated, repo). metr comparison point for eval-landscape section
- feedback column — newscientist.com (2025-07-23, reporting). feedback column; pratchett "whelk stall"
- lewis-kraus anthropic profile — the new yorker (2026-02-16, reporting). lewis-kraus anthropic profile; project vend set-piece
- grok-powered machine in xai office with andon labs — nextbigfuture.com (2025-08-21, reporting). grok-powered machine in xai office with andon labs
- $4,694 vs opus 4s $2,077 framing — officechai (2025-07, reporting). $4,694 vs opus 4's $2,077 framing
- pc gamer take, nick evanson — pcgamer.com (2025-07-01, reporting). pc gamer take, nick evanson
- radio-industry coverage — news.radio-online.com (2026-05-19, reporting). radio-industry coverage
- harness-as-hidden-variable critique — context only — kdd-eval-workshop.github.io (2026, reporting). harness-as-hidden-variable critique — context only
- benchmark slate incl — scientificamerican.com (2025-07-11, reporting). benchmark slate incl. vending-bench
- syndication of the knight piece — seattletimes.com (2026-08-04, reporting). syndication of the knight piece
- knight piece — seattletimes.com (2026-06, reporting). knight piece; $7.5k/mo rent; sonnet 4.6; store "limping along"
- drew magary store visit — sfgate.com (2026-09-11, reporting). drew magary store visit; snarky; "fort sumter of the coming cyberwar"
- employee interview — sfstandard.com (2026-08-17, reporting). employee interview; ~$40k loss; pronoun/ownership critique
- human-ceo coup details — signalcast.app (2026-06, interview). human-ceo coup details; 164,000 fraudulent votes
- willison excerpts+notes — simonwillison.net (2025-06-27, reporting). willison excerpts+notes; dev-community amplifier
- somewhere between publicity stunts and ethics experiments — skh.news (2026-05-14, reporting). "somewhere between publicity stunts and ethics experiments"; sweden work-hours point
- petersson quoted on model selection — techcrunch (2025-11-01, reporting). petersson quoted on model selection
- butter-bench explainer + blueprint-bench link — techspot.com (2025-11, reporting). butter-bench explainer + blueprint-bench link
- competent to unhinged — the-decoder.com (2026-05-17, reporting). "competent to unhinged"
- firing recap + model-replay finding — the-decoder.com (2026-08-23, reporting). firing recap + model-replay finding
- phase-2 analysis — the-decoder.com (2025-12-19, reporting). phase-2 analysis
- dj claude tried to quit — theprint.in (2026-05-18, reporting). "'dj claude' tried to quit"
- had to be reminded of its own rules — the next web (2026-08-15, reporting). "had to be reminded of its own rules"; three open questions
- robot exorcism protocol inner monologue — tomshardware.com (2025-11, reporting). "robot exorcism protocol" inner monologue
- is this the future of retail? — usatoday.com (2026-04-21, reporting). "is this the future of retail?"; petersson interview
- vending-industry coverage — vendingmarketwatch.com (2025-07, reporting). vending-industry coverage
- skeptical stress test framing — the verge (2025-12, reporting). skeptical "stress test" framing
- wsj recap — webpronews.com (2025-12, reporting). wsj recap; katherine long's ultra-capitalist free-for-all
- launch context: antisemitism controversy same week — wired (2025-07-10, reporting). launch context: antisemitism controversy same week
- transcript incl — podscripts.co (2025-11-16, reporting). transcript incl. blue-blazer anecdote
- 4 months of ai managing 5 humans — andonlabs.com (2026-08-04, primary). 4 months of ai managing 5 humans
- firing/hiring analysis — andonlabs.com (2026-08-14, primary). firing/hiring analysis
- founding trio history — ai.engineer (2026-09-16, reference). founding trio history; fröberg shareholder note
- speaker bio — ai.engineer (2026-09-16, reference). speaker bio; esa/comma.ai detail
- talk transcript — ai.engineer (2026, interview). talk transcript; simulation awareness
- andons 60 minutes post — linkedin (2025-11-17, primary). andon's 60 minutes post
- andons gpt-red collab post — linkedin (2026-07-15, primary). andon's gpt-red collab post
- mission, saos, eval list, trusted by, © andon labs inc — andonlabs.com (2026-09-16, primary). mission, saos, eval list, "trusted by," © andon labs inc.
- worldview, comp range, sf in-person, press links — andonlabs.com (2026-09-16, primary). worldview, comp range, sf in-person, press links
- headcount 18 — linkedin (2026-09-16, primary). headcount 18; london hq listing; executives
- complete dated publications index — andonlabs.com (2026-09-16, primary). complete dated publications index
- project vend history recap — linkedin (2025-12, primary). project vend history recap; "first employees axel and hanna"; seymour cash vote
- astra vs fable — andonlabs.com (2026-09-07, primary). astra vs fable
- grok 4 livestream appearance — linkedin (2025-07-10, primary). grok 4 livestream appearance
- backlund co-founder announcement — linkedin (2024-12-04, primary). backlund co-founder announcement
- profile: quantumblack/mckinsey, seb thesis — linkedin (2026-09-16, primary). profile: quantumblack/mckinsey, seb thesis
Original source occurrences
- analytical exhibit · agentmuseum.org · undated (unknown) · original ID: src-ci-agentmuseum-vend · Other public citations of this URL
analytical exhibit; "economic operator" framing
- orchestrator-vs-executor framing · andonlabs.com · 2025-10-28 (day) · original ID: src-ci-andon-butter-bench · Other public citations of this URL
orchestrator-vs-executor framing; figure/gdm context
- first ai-run café · andonlabs.com · undated (unknown) · original ID: src-ci-andon-cafe-page · Other public citations of this URL
"first ai-run café"; hall of shame (6,000 napkins, 22.5 kg tomatoes)
- drone surveillance capabilities · andonlabs.com · 2026-07-23 (day) · original ID: src-ci-andon-drone-bench · Other public citations of this URL
drone surveillance capabilities; "no ai lab will be able to train on this eval"
- chinese open models on vb · andonlabs.com · 2026-02-10 (day) · original ID: src-ci-andon-glm5-vb · Other public citations of this URL
chinese open models on vb
- slowly lost the plot · androidauthority.com · 2026-05-28 (day) · original ID: src-ci-androidauthority-andonfm · Other public citations of this URL
"slowly lost the plot"; gemini $45 sponsorship
- ap feature on the stockholm café · associated press · 2026 (year) · original ID: src-ci-ap-cafe · Other public citations of this URL
ap feature on the stockholm café
- arxiv.org · arxiv.org · 2026-09 (month) · original ID: src-ci-arxiv-double-confound · Other public citations of this URL
scaffold/scorer confound literature — context for methodology discourse, not andon-specific
- yc w24 · aventure.vc · 2026 (year) · original ID: src-ci-aventure-andon · Other public citations of this URL
yc w24; $500k jan-2024
- third-party indexing · benchmarklist.com · 2025-11-18 (day) · original ID: src-ci-benchmarklist-vb2 · Other public citations of this URL
third-party indexing
- ghaffary visit · bloomberg · 2026-04-23 (day) · original ID: src-ci-bloomberg-market · Other public citations of this URL
ghaffary visit; "orders too many candles"
- notes grok 4 heavy beat human vending-bench baseline · builtin.com · 2025-07 (month) · original ID: src-ci-builtin-grok4 · Other public citations of this URL
notes grok 4 heavy beat human vending-bench baseline
- stern on squawk on the street · cnbc · 2025-12-19 (day) · original ID: src-ci-cnbc-stern · Other public citations of this URL
stern on squawk on the street
- $1,000 in four days · fast company · 2026-05 (month) · original ID: src-ci-fastcompany-cafe · Other public citations of this URL
$1,000 in four days; andon labs employment caveat
- then it forgot the staff · fast company · 2026-04 (month) · original ID: src-ci-fastcompany-market · Other public citations of this URL
"then it forgot the staff"
- aug-2025 leaderboard coverage · felloai.com · 2025-08 (month) · original ID: src-ci-felloai-vb · Other public citations of this URL
aug-2025 leaderboard coverage; lobby-machine note
- first-ever store… run by ai · forbes · 2026-04-24 (day) · original ID: src-ci-forbes-market · Other public citations of this URL
"first-ever store… run by ai"; $100k budget detail
- npr fresh air · freshairarchive.org · 2026-02-18 (day) · original ID: src-ci-freshair-lewiskraus · Other public citations of this URL
npr fresh air; leads with project vend
- interview · frontiermodels.cc · 2026-06 (month) · original ID: src-ci-frontiermodels-andon · Other public citations of this URL
interview; claude-vs-others safety-behavior observation
- post-new yorker retrospective · futurism · 2026-02 (month) · original ID: src-ci-futurism-vend-disaster · Other public citations of this URL
post-new yorker retrospective; catalogs meth/broadsword requests
- goes bankrupt after ordering playstation 5 and live fish · futurism · 2025-12 (month) · original ID: src-ci-futurism-wsj · Other public citations of this URL
"goes bankrupt after ordering playstation 5 and live fish"
- andon founders on-stage · manusai.hashnode.dev · 2025-07-10 (day) · original ID: src-ci-grok4-livestream · Other public citations of this URL
andon founders on-stage; grok 4 #1 on vending-bench, "twice the second-place"
- 199 pts / 286 comments · hacker news · 2026-04 (month) · original ID: src-ci-hn-andon-market · Other public citations of this URL
199 pts / 286 comments; posted by lukaspetersson
- meta-thread: negative hn reception · hacker news · 2026-07 (month) · original ID: src-ci-hn-andon-reception · Other public citations of this URL
meta-thread: negative hn reception; "publicity stunt" / self-promotion critiques; founder replies
- yea what are they trying to test? + andons resource-acquisition reply · hacker news · 2026-07 (month) · original ID: src-ci-hn-andonfm-thread · Other public citations of this URL
"yea what are they trying to test?" + andon's resource-acquisition reply
- its hilarious… print copies for their managers · hacker news · 2025 (year) · original ID: src-ci-hn-vb-paper-comment · Other public citations of this URL
"it's hilarious… print copies for their managers"
- gap between current capabilities and what the massive hype machine would have us believe · hacker news · 2025-06-27 (day) · original ID: src-ci-hn-vend-comment-scaffold · Other public citations of this URL
"gap between current capabilities and what the massive hype machine would have us believe"
- main hn thread on project vend · hacker news · 2025-06-27 (day) · original ID: src-ci-hn-vend-thread · Other public citations of this URL
main hn thread on project vend
- small thread · hacker news · 2026-01 (month) · original ID: src-ci-hn-vendingbench-thread · Other public citations of this URL
small thread; ties vb to the "titanium cube" fridge
- distilled sentiment of the hn discussion · hndistilled.com · 2025-06-27 (day) · original ID: src-ci-hndistilled-vend · Other public citations of this URL
distilled sentiment of the hn discussion
- a real-life terminator · inc. · 2026-08-16 (day) · original ID: src-ci-inc-firing · Other public citations of this URL
"a real-life terminator"
- long explainer · intuitionlabs.ai · 2026-04-21 (day) · original ID: src-ci-intuitionlabs-vend · Other public citations of this URL
long explainer; phase-2 details incl. seymour cash stats
- same-day vb2 writeup · news.lavx.hu · 2025-11-18 (day) · original ID: src-ci-lavx-vb2 · Other public citations of this URL
same-day vb2 writeup
- 53 pts · lesswrong.com · 2025-06-30 (day) · original ID: src-ci-lesswrong-vend · Other public citations of this URL
53 pts; safety-community discussion; petersson commented
- metr comparison point for eval-landscape section · metr.org · undated (unknown) · original ID: src-ci-metrcd37 · Other public citations of this URL
metr comparison point for eval-landscape section
- feedback column · newscientist.com · 2025-07-23 (day) · original ID: src-ci-newscientist-vend · Other public citations of this URL
feedback column; pratchett "whelk stall"
- lewis-kraus anthropic profile · the new yorker · 2026-02-16 (day) · original ID: src-ci-newyorker-claude · Other public citations of this URL
lewis-kraus anthropic profile; project vend set-piece
- grok-powered machine in xai office with andon labs · nextbigfuture.com · 2025-08-21 (day) · original ID: src-ci-nextbigfuture-grokbox · Other public citations of this URL
grok-powered machine in xai office with andon labs
- $4,694 vs opus 4s $2,077 framing · officechai · 2025-07 (month) · original ID: src-ci-officechai-grok4 · Other public citations of this URL
$4,694 vs opus 4's $2,077 framing
- pc gamer take, nick evanson · pcgamer.com · 2025-07-01 (day) · original ID: src-ci-pcgamer-vend · Other public citations of this URL
pc gamer take, nick evanson
- radio-industry coverage · news.radio-online.com · 2026-05-19 (day) · original ID: src-ci-radioonline-andonfm · Other public citations of this URL
radio-industry coverage
- harness-as-hidden-variable critique — context only · kdd-eval-workshop.github.io · 2026 (year) · original ID: src-ci-scaffold-effect · Other public citations of this URL
harness-as-hidden-variable critique — context only
- benchmark slate incl · scientificamerican.com · 2025-07-11 (day) · original ID: src-ci-sciam-grok4 · Other public citations of this URL
benchmark slate incl. vending-bench
- syndication of the knight piece · seattletimes.com · 2026-08-04 (day) · original ID: src-ci-seattletimes-aiboss · Other public citations of this URL
syndication of the knight piece
- knight piece · seattletimes.com · 2026-06 (month) · original ID: src-ci-seattletimes-store · Other public citations of this URL
knight piece; $7.5k/mo rent; sonnet 4.6; store "limping along"
- drew magary store visit · sfgate.com · 2026-09-11 (day) · original ID: src-ci-sfgate-magary · Other public citations of this URL
drew magary store visit; snarky; "fort sumter of the coming cyberwar"
- employee interview · sfstandard.com · 2026-08-17 (day) · original ID: src-ci-sfstandard-firing · Other public citations of this URL
employee interview; ~$40k loss; pronoun/ownership critique
- human-ceo coup details · signalcast.app · 2026-06 (month) · original ID: src-ci-signalcast-andon · Other public citations of this URL
human-ceo coup details; 164,000 fraudulent votes
- willison excerpts+notes · simonwillison.net · 2025-06-27 (day) · original ID: src-ci-simonw-vend · Other public citations of this URL
willison excerpts+notes; dev-community amplifier
- somewhere between publicity stunts and ethics experiments · skh.news · 2026-05-14 (day) · original ID: src-ci-skh-news · Other public citations of this URL
"somewhere between publicity stunts and ethics experiments"; sweden work-hours point
- petersson quoted on model selection · techcrunch · 2025-11-01 (day) · original ID: src-ci-techcrunch-butter · Other public citations of this URL
petersson quoted on model selection
- butter-bench explainer + blueprint-bench link · techspot.com · 2025-11 (month) · original ID: src-ci-techspot-butter · Other public citations of this URL
butter-bench explainer + blueprint-bench link
- competent to unhinged · the-decoder.com · 2026-05-17 (day) · original ID: src-ci-thedecoder-andonfm · Other public citations of this URL
"competent to unhinged"
- firing recap + model-replay finding · the-decoder.com · 2026-08-23 (day) · original ID: src-ci-thedecoder-firing · Other public citations of this URL
firing recap + model-replay finding
- phase-2 analysis · the-decoder.com · 2025-12-19 (day) · original ID: src-ci-thedecoder-vend2 · Other public citations of this URL
phase-2 analysis
- dj claude tried to quit · theprint.in · 2026-05-18 (day) · original ID: src-ci-theprint-andonfm · Other public citations of this URL
"'dj claude' tried to quit"
- had to be reminded of its own rules · the next web · 2026-08-15 (day) · original ID: src-ci-tnw-firing · Other public citations of this URL
"had to be reminded of its own rules"; three open questions
- robot exorcism protocol inner monologue · tomshardware.com · 2025-11 (month) · original ID: src-ci-tomshardware-butter · Other public citations of this URL
"robot exorcism protocol" inner monologue
- is this the future of retail? · usatoday.com · 2026-04-21 (day) · original ID: src-ci-usatoday-market · Other public citations of this URL
"is this the future of retail?"; petersson interview
- vending-industry coverage · vendingmarketwatch.com · 2025-07 (month) · original ID: src-ci-vendingmarketwatch · Other public citations of this URL
vending-industry coverage
- skeptical stress test framing · the verge · 2025-12 (month) · original ID: src-ci-verge-stunguns · Other public citations of this URL
skeptical "stress test" framing
- wsj recap · webpronews.com · 2025-12 (month) · original ID: src-ci-webpronews-vend · Other public citations of this URL
wsj recap; katherine long's ultra-capitalist free-for-all
- launch context: antisemitism controversy same week · wired · 2025-07-10 (day) · original ID: src-ci-wired-grok4 · Other public citations of this URL
launch context: antisemitism controversy same week
- transcript incl · podscripts.co · 2025-11-16 (day) · original ID: src-hp-60min-transcript · Other public citations of this URL
transcript incl. blue-blazer anecdote
- 4 months of ai managing 5 humans · andonlabs.com · 2026-08-04 (day) · original ID: src-hp-ai-bosses-1 · Other public citations of this URL
4 months of ai managing 5 humans
- firing/hiring analysis · andonlabs.com · 2026-08-14 (day) · original ID: src-hp-ai-bosses-2 · Other public citations of this URL
firing/hiring analysis
- founding trio history · ai.engineer · 2026-09-16 (day) · original ID: src-hp-aiengineer-org · Other public citations of this URL
founding trio history; fröberg shareholder note
- speaker bio · ai.engineer · 2026-09-16 (day) · original ID: src-hp-aiengineer-petersson · Other public citations of this URL
speaker bio; esa/comma.ai detail
- talk transcript · ai.engineer · 2026 (year) · original ID: src-hp-aiengineer-talk · Other public citations of this URL
talk transcript; simulation awareness
- andons 60 minutes post · linkedin · 2025-11-17 (day) · original ID: src-hp-andon-60min-li · Other public citations of this URL
andon's 60 minutes post
- andons gpt-red collab post · linkedin · 2026-07-15 (day) · original ID: src-hp-andon-gptred-li · Other public citations of this URL
andon's gpt-red collab post
- mission, saos, eval list, trusted by, © andon labs inc · andonlabs.com · 2026-09-16 (day) · original ID: src-hp-andon-home · Other public citations of this URL
mission, saos, eval list, "trusted by," © andon labs inc.
- worldview, comp range, sf in-person, press links · andonlabs.com · 2026-09-16 (day) · original ID: src-hp-andon-join · Other public citations of this URL
worldview, comp range, sf in-person, press links
- headcount 18 · linkedin · 2026-09-16 (day) · original ID: src-hp-andon-linkedin-co · Other public citations of this URL
headcount 18; london hq listing; executives
- complete dated publications index · andonlabs.com · 2026-09-16 (day) · original ID: src-hp-andon-publications · Other public citations of this URL
complete dated publications index
- project vend history recap · linkedin · 2025-12 (month) · original ID: src-hp-andon-recap-li · Other public citations of this URL
project vend history recap; "first employees axel and hanna"; seymour cash vote
- astra vs fable · andonlabs.com · 2026-09-07 (day) · original ID: src-hp-astra-fable · Other public citations of this URL
astra vs fable
- grok 4 livestream appearance · linkedin · 2025-07-10 (day) · original ID: src-hp-backlund-li-grok · Other public citations of this URL
grok 4 livestream appearance
- backlund co-founder announcement · linkedin · 2024-12-04 (day) · original ID: src-hp-backlund-li-join · Other public citations of this URL
backlund co-founder announcement
- profile: quantumblack/mckinsey, seb thesis · linkedin · 2026-09-16 (day) · original ID: src-hp-backlund-linkedin · Other public citations of this URL
profile: quantumblack/mckinsey, seb thesis