Falcons at Saints: New Orleans Is the Pick, Not a Lock
Both frozen Week 4 forecasts pick New Orleans on Monday night, but 67.6% in the original and 53.0% in the rebuild describe very different levels of confidence.
All Blog Posts
-
-
Lions at Panthers: Detroit Is the Pick, but the Models Are Split
Detroit is 57.6% in the original Week 4 forecast and 53.2% in the rebuild, but the component models and separate point forecasts make Sunday night far less settled.
-
Cleveland Won 27–24. Right Side, Low Total
Both Week 4 forecasts picked Cleveland. The rebuilt point model nearly matched the three-point margin, but undershot the total. Grade the winner, spread and points, then look toward Sunday.
-
Steelers at Browns: The Models Lean Cleveland. The Market Favors Pittsburgh
Cleveland is 51.9% in the rebuilt forecast versus 70.4% in the original. Thursday's prices favor Pittsburgh, while a falling total tests which saved estimates still apply.
-
NFL Week 4: Two Forecasts, Three Changed Picks
The full five-model Week 4 board, before and after retraining: three changed winners, lower confidence, and the model disagreements behind both forecast versions.
-
I Added a Search Dock to My Blog
A small dock for a sprawling blog: local search, section jumps, keyboard shortcuts, and a little animation to make the archive easier to explore.
-
Why I'm Building Agent Model Fit
Agentic development has become a project of its own. Agent Model Fit is where I'm working through how agents, models, and real problems fit together.
-
Atlanta Won 35–14. All Three Models Picked Green Bay
Atlanta dominated Green Bay 35–14. Every contributing model missed, and sharpening increased the scoring penalty. The preserved forecasts and 33-game record get graded.
-
Falcons at Packers: Green Bay Is the Pick. The Edge Depends on Confidence
All three models favor Green Bay, but Wednesday's -250 price sits between the raw and final probabilities. Penix returns as Week 3 tests the confidence adjustment.
-
NFL Week 3: Bayesian Is Back. The Confidence Test Continues
Three models contribute again, six favorites exceed 90%, and three ensemble picks follow a single model. The complete September 22 Week 3 forecast.
-
NFL Week 2: Eleven Picks Above 90%. Five Winners
The original Week 2 ensemble went 8–8. Its eleven 90%-plus favorites went 5–6, and sharpening again made the probability scores worse.
-
Giants at Rams: New York Gets 92.3%. Elo Takes the Other Side
The corrected forecast picks the Giants at 92.3%, up from a 73.0% raw blend. Bayesian is back, Elo favors the Rams, and both versions stay in the record.
-
Buffalo Won 41–31. This Time, the Extra Confidence Helped
Buffalo beat Detroit 41–31. All three available models picked the winner, and sharpening improved the probability scores. The full record still favors the raw blend.
-
Lions at Bills: Three Forecasts Favor Buffalo. Two Drive the Ensemble
Buffalo gets 79.4% against Detroit, up from a 63.1% raw blend. Three forecasts favor the Bills, but Bayesian is excluded from this week's ensemble. Here is the pick and how either result will be graded.
-
NFL Week 2 2026: The Forecast Got Louder. The Ensemble Got Smaller
Eleven Week 2 favorites clear 90%, but only two models contribute to the saved ensemble. The full board, the disagreements, and the confidence test ahead.
-
NFL Week 1: A 9–7 Record Hid the Cost of Confidence
The frozen Week 1 board finished 9–7. Grading all 16 games shows that temperature scaling kept every pick and made the probability scores worse.
-
The 49ers Won 27–7. My 93.6% Rams Pick Was Wrong
San Francisco beat Los Angeles 27–7 after my final forecast gave the 49ers just 6.4%. Grading the miss, the cost of extra confidence, and the first two games of the record.
-
49ers vs. Rams: Three Models Pick Los Angeles. None Says 94%
The Rams get 93.6% in the saved Week 1 forecast. The raw blend is 74.5%. A Melbourne preview about model agreement, amplified confidence, and how to grade either result.
-
Seattle Won 13–10. The Confidence Question Is Still Open
All three models picked Seattle, and Seattle won 13–10. Grading the frozen forecast shows what went right—and why one result cannot validate its confidence.
-
Patriots at Seahawks: Three Models Pick Seattle. Only One Sounds Sure
Seattle gets a 70.9% win probability in the season opener, but the model-by-model view is much closer. A Patriots–Seahawks deep dive with a link to the full Week 1 prediction board.
-
NFL Week 1 2026: The Model Is Ready. The Confidence Still Has to Prove Itself
The 2026 opener arrives with a repaired three-model ensemble, five huge favorites, six disagreement games, and one important warning: confidence is not the same as calibration.
-
NFL Week 13 2025: The 28.4% Edge, Thanksgiving Aftermath, and Why the Market is Sleeping on Seattle
Week 13 brings the biggest betting edge of the season (MIN @ SEA, +28.4%), three Thursday games, and a Rams team ready to destroy Carolina. Plus: 7 consensus picks and why the models love underdogs this week.
-
NFL Week 12 Results: XGBoost's Revenge Tour & The Perfect Consensus
Breaking down how our ensemble model went 10-4, XGBoost surged to 85.7%, and every single consensus pick hit. Plus: the four upsets that kept things interesting.
-
NFL Week 12 2025: The 35.6% Edge, Five Coin Flips, and Why Seattle @ Tennessee Is the Lock of the Year
Week 12 brings the biggest value opportunity of the season (NE @ CIN), five true toss-ups including Thursday's BUF @ HOU, and Seattle traveling to Tennessee as 87.9% favorites—the most confident pick we've made all year.
-
NFL Week 10 2025: Three Road Favorites Over 75%, and Why Detroit @ Washington Is the Week's Wildest Bet
Week 10 features three brazen road favorites above 75% confidence, a Thursday night trap game, and DET @ WAS—the most confident pick of the week that somehow carries the worst betting value.
-
LV @ DEN Thursday Night Week 10: When 7-2 Hosts 2-6, Can the Spread Tell the Story?
Denver (7-2) is an 85.5% favorite at home against Las Vegas (2-6), but the models project only a 5.7-point win. Is DEN -9.0 too much?
-
Week 9 Results: When the 'Lock of the Week' Implodes and the Models Hit the Wall
The models face-planted on game prediction (50% accuracy) and barely stayed above .500 on spreads (57.1% ATS). Also: Chicago and Cincinnati decided gravity was optional.
-
NFL Week 9 2025: Five Unanimous Picks, Two Primetime Coin Flips, and Sneaky Value
Week 9 trims the chaos: 5 games have complete model agreement, while IND@PIT and KC@BUF headline as coin-flip shootouts with market edges hiding in plain sight.
-
BAL @ MIA Week 9: When Both Teams Are Broken—A Tale of Two 1-4 Teams
Baltimore travels to Miami in a battle of 1-4 disappointments. The models are fighting again, Vegas sees a blowout, and our predictions suggest massive betting value—or a trap.
-
Week 8 Autopsy: When Consensus Wasn't Enough and Chaos Reigned Supreme
The models promised consensus. Week 8 delivered carnage. Five high-confidence predictions failed, XGBoost emerged as the lone survivor, and the season's most divisive game taught us a brutal lesson about overconfidence.
-
When Models Go to War: Chicago @ Baltimore and the Art of Prediction Disagreement
The Bears-Ravens matchup is the most divisive game of the 2025 season. Why do prediction models disagree so dramatically, and what does it teach us about football analytics?
-
Setting Up Ollama with BrowserOS: Local AI Configuration Guide
Step-by-step guide to configuring Ollama as a local AI provider for BrowserOS. Complete setup instructions including CORS configuration and model integration.
-
NFL Week 8 2025: The Consensus Week - When 10 Games Unite the Models
Week 8 brings unprecedented model agreement with 10 consensus picks—and one game that has the models fighting harder than any matchup this season.
-
The Sharp & pnpm Vercel Build Nightmare (And How I Fixed It)
Fighting with Sharp, pnpm, and Vercel for an hour. Here's what finally worked when image optimization kept failing.
-
NFL Week 7 2025 Results: When the Models Unite - Consensus Crushes, Upsets Strike
Week 7 delivered a masterclass in the power of consensus—and a humbling reminder that even 87% confidence can't predict Thursday Night Football chaos.
-
How the Model 'Sees' Each Team: A Story of Calibration and Surprise
Exploring how our NFL prediction model understands each team through the lens of predicted vs actual performance. Some teams are exactly who the model thought they were. Others? Complete surprises.
-
NFL Week 7 2025: Predictions Battle - When Models Disagree
A deep dive into Week 7 NFL predictions, analyzing where five different prediction models agree—and where they wildly disagree.
-
-
-
2025 MLB Season: Fan Sentiment on the Torpedo Bat
Exploring baseball fan reactions to the innovative 'torpedo bat' in the 2025 MLB season, based on posts from X.
tags:
-
Posting to My Site with Grok and GitHub from My iPad Because Effort’s Overrated
Too lazy to get off the couch, so I’m using Grok and GitHub on my iPad to push posts to my site. Here’s the slacker’s guide.
-
WWE Raw April 7, 2025: Fan Sentiment Shines with an A- Grade
Analyzing fan sentiment for WWE Raw on April 7, 2025, straight from posts on X.
tags:
-
2025 March Madness: Fan Sentiment Analysis
Analyzing fan sentiment for 2025 March Madness, straight from posts on X.
tags:
-
AEW Dynasty 2025
Resuls, recap, and general sentiment of AEW Dynasty 2025, straight from posts on X.
tags:
-
My Website Was Down, So I Threw One Up on Vercel
My website was down, no big deal. Deployed a Vercel template in like 5 minutes. Here’s the lazy tale thanks to Grok.
tags:
