Daniel Deusing — Developer, Founder, Father of FourDaniel Deusing — software developer and founder of twiceD, father of four in Ribeirão Claro, Brazil. Notes on code, AI, football and a daily AI newspaper.https://danieldeusing.de/The final ledger: everything my World Cup AI got right, got wrong, and actually earnedhttps://danieldeusing.de/articles/ai-predictions-graded-final-ledger/https://danieldeusing.de/articles/ai-predictions-graded-final-ledger/The World Cup is over: Spain champions, my AI-managed fantasy team first by 104 points — and this closing piece audits the whole experiment. All eight report cards revisited: 103 graded match tips (62.1% winners, a floor held by 0.14), 984 graded lineup calls (81.8%, cleanly calibrated), every bug and overcorrection, what the title actually earned, where the AI added real value and where it merely matched the market — and what I'd tell you before you run the same play on a problem of yours.Mon, 20 Jul 2026 00:00:00 GMTZero of two: the round where the right fix was no fixhttps://danieldeusing.de/articles/ai-predictions-graded-semifinals/https://danieldeusing.de/articles/ai-predictions-graded-semifinals/The semifinals, graded in public: my World Cup fantasy AI called 0 of 2 winners — both games priced as coin flips by the market, both tipped as coin flips, both lost. Its postmortem concluded nothing needs to change, and after checking, I co-sign it. On telling outcome noise from process failure, retiring a KPI that can no longer be moved, and the starting-eleven pattern that expired.Thu, 16 Jul 2026 14:00:00 GMTFour of four: the AI's best round of the tournament — and the scoreboard came back emptyhttps://danieldeusing.de/articles/ai-predictions-graded-quarterfinals/https://danieldeusing.de/articles/ai-predictions-graded-quarterfinals/The quarterfinals, graded in public: my World Cup fantasy AI called 4 of 4 winners with 3 exact scores — its best round yet, one round after its worst. And when the grader ran, all four tips had silently vanished from the scoreboard: a second format bug, one layer below the fix for the first. Plus the metric that punished a perfect round, and a league lead that grew from 55 to 95.Thu, 16 Jul 2026 09:00:00 GMTTwo of eight: the AI's worst round of the tournament — and the three very different ways it got therehttps://danieldeusing.de/articles/ai-predictions-graded-round-of-16/https://danieldeusing.de/articles/ai-predictions-graded-round-of-16/The Round of 16, graded in public: my World Cup fantasy AI called 2 of 8 winners — its worst round yet. Taken apart, the wreckage splits into a clerical bug that cost two correct calls, a safety rule that overshot, and coinflips lost fairly. Meanwhile the quiet half had its best round, and the league lead exploded from five points to fifty-five.Thu, 09 Jul 2026 00:00:00 GMTThe public scorecard reaches the knockouts: the AI called its sharpest scores yet — and walked straight back into the trap it had just escapedhttps://danieldeusing.de/articles/ai-predictions-graded-round-of-32/https://danieldeusing.de/articles/ai-predictions-graded-round-of-32/The first knockout round of grading my World Cup fantasy AI in public: I finally cleaned the scoreboard I said I couldn't trust, the score predictions got their sharpest yet — and the confidence discipline walked straight back into an old overconfidence trap it had just escaped.Sun, 05 Jul 2026 00:00:00 GMTRound three of the public scorecard: the AI learned to doubt again — and fumbled the one thing it was best athttps://danieldeusing.de/articles/ai-predictions-graded-matchday-3/https://danieldeusing.de/articles/ai-predictions-graded-matchday-3/Round three of grading my World Cup fantasy AI in public: it got its self-doubt back — the widest confidence gap of the group stage — while the quiet half that's actually winning me the league handed me a stranger problem. I went to grade it and couldn't trust my own scoreboard.Fri, 03 Jul 2026 00:00:00 GMTRound two of the public scorecard: the predictions got sharp — and went quiet about when they're wronghttps://danieldeusing.de/articles/ai-predictions-graded-matchday-2/https://danieldeusing.de/articles/ai-predictions-graded-matchday-2/Round two of grading my World Cup fantasy AI in public: the match-result predictions jumped from 46% to 75% — and the same data shows it got no better at knowing when it's wrong.Thu, 25 Jun 2026 00:00:00 GMTPredictions, graded honestly: good at calling who'll play, weak at calling the scorehttps://danieldeusing.de/articles/ai-predictions-graded-matchday-1/https://danieldeusing.de/articles/ai-predictions-graded-matchday-1/After one World Cup matchday, I graded my AI agents' predictions against reality in public — reliable at calling who'll play, weak at calling the score, and the grader itself had bugs I had to fix first.Mon, 22 Jun 2026 00:00:00 GMTI built a team of AI agents to do my fantasy-football homeworkhttps://danieldeusing.de/articles/ai-agents-fantasy-football/https://danieldeusing.de/articles/ai-agents-fantasy-football/Every morning a team of AI agents logs into my Comunio World Cup league, reads the real football news, fact-checks itself and leaves me one dashboard — plus a growing intelligence file on the rivals I'm bidding against.Wed, 10 Jun 2026 00:00:00 GMTEvery morning, an AI writes me my own newspaperhttps://danieldeusing.de/articles/ai-morning-newspaper/https://danieldeusing.de/articles/ai-morning-newspaper/A small team of AI agents researches, writes, fact-checks and translates a personalized morning paper for me — and explains every term I don't know with a real-life comparison.Thu, 04 Jun 2026 00:00:00 GMT