Forecasting Under Fire: The Pause
It was 23:48 on Tuesday. My forecast was locked at $123.53. Twelve minutes earlier, Trump agreed to suspend the bombing. I watched the oil forecast decay in real time.
settle in
- forecasting
- bayesian
- experiments
- oil
Notes
Loose, unopinionated notes on things I don't entirely understand yet.
Lower commitment than essays. More permanent than a social media post. Thinking out loud, in public, slowly.
Active series
Forecasting Under Fire →
Can Bayesian forecasting beat Goldman Sachs during an oil crisis? 8-week experiment. Methodology public. Results documented. Ego at risk.
Catching Meta Red-Handed →
I built a script to track my own Threads suppression. Then a Meta insider confirmed the pattern. Four-part investigation, documented as it unfolds. Starting with the data.
Building in the Open →
Building Rainforest Studio's Living Archive. Specifics over theory. Starting with the two data model rewrites.
Pick one and come along.
The Attention Economy is Shifting...again
Pattern spotting the current attention economy shift, and building an external memory so I stop forgetting what I'm seeing
a coffee's worth
- attention-economy
- observations
- supabase
- pattern spotting
- cost of living
- social media platforms
Forecasting Under Fire: Week 4
Easter Sunday. Power Plant Day. The model overcalled Week 3 by $10, the physical market is at $141, and Trump is posting about Allah at 8am.
settle in
- forecasting
- bayesian
- experiments
- oil
Forecasting Under Fire: Week 3 Outcomes
$9.83 off. Direction wrong for the first time. The model predicted up, Brent went down. Three weeks, three losses to baseline. But the physical market is telling a different story.
a coffee's worth
- forecasting
- bayesian
- experiments
- oil
I looked at my own site and felt nothing
Second post in a series about building Rainforest Studio. Starting with the moment I realised the site looked like every other tech startup.
a coffee's worth
- rainforest-studio
- building-in-the-open
- design
- cultural-technology
- AI
Forecasting Under Fire: Week 3
Brent crude forecast for 2 April 2026. The band broke. Houthis are in. The model is predicting $118.88 into a four day week with Good Friday closing markets early.
settle in
- forecasting
- bayesian
- experiments
- oil
Forecasting Under Fire: Week 2 Outcomes
$1.32 off. The model nailed the price but the naive baseline still won. Week 2 of an 8-week oil price forecasting experiment during the Iran war, scored honestly.
settle in
- forecasting
- bayesian
- experiments
- oil
I Posted About Threads Suppression. Threads Gave It 0 Views
I posted about Threads suppression on Threads itself. The post got 0 views and wouldn't load. The platform proved the thesis while I was writing about it.
a coffee's worth
- social-media
- algorithms
- threads
- meta
- data-analysis
Forecasting Under Fire: Week 2
Brent crude forecast for 27 March 2026. Point estimate $108.16 after the model learned from Week 1's overshoot. Trump's Hormuz ultimatum could break everything.
a coffee's worth
- forecasting
- bayesian
- experiments
- oil
Forecasting Under Fire: Week 1 Outcomes
My Brent crude forecast overshot by $13.75. The naive baseline won. Week 1 of an 8-week oil price forecasting experiment during the Iran war, scored honestly.
a coffee's worth
- forecasting
- bayesian
- experiments
- oil
A Meta Employee Confirmed Threads Suppression
I posted my Threads suppression data on LinkedIn. A Trust & Safety Specialist at Meta commented saying it highlights what people inside already suspected.
a coffee's worth
- social-media
- algorithms
- threads
- meta
- data-analysis
Forecasting Under Fire: Week 1 — The Experiment Begins
First forecast locked. Brent at $99.47. Eight weeks of updating beliefs under fire starts now.
a coffee's worth
- forecasting
- oil
- iran-war
- bayesian-thinking
- public-learning
Forecasting Under Fire: Week 1
Starting an 8-week experiment. Can systematic Bayesian updating beat Goldman Sachs' oil forecasts during a geopolitical crisis? Week 1 methodology and baseline.
a quick one
- forecasting
- bayesian
- experiments
Forecasting Under Fire, The Experiment
Eight weeks. One question. Can systematic Bayesian updating beat Goldman Sachs during an oil crisis? The methodology is public from day one. The ego risk is real.
a coffee's worth
- forecasting
- bayesian
- experiments
- oil
717 Views, 1 Like. How I Caught Threads Suppressing My Posts
My Threads engagement dropped 30x overnight. I built a script to pull 30 days of data and found evidence of algorithmic suppression. Here's what the numbers showed.
a coffee's worth
- social-media
- algorithms
- threads
- meta
- data-analysis
Building in the Open: What Actually Happened This Week
Week 1 of documenting Living Archive's development publicly. What's hard, what's working, and why the data model changed twice before we shipped anything.
a quick one
- rainforest-studio
- living-archive
- building-in-the-open