When the actor in your systems is an AI
Anthropic, Grab and Meta each shipped infrastructure work this week that, read together, sketches the early blueprint for running autonomous AI agents safely inside a real company.
3 papers
Engineering
Explainer
Explainer
// plain-english deep dives into the research shaping the field
Why forecasts are becoming decision systems
Prediction is turning into a commodity. The value is migrating to everything around it — calibration, execution, reusable representations, and the decision a forecast is actually meant to serve.
6 papers
Recent analysis
The bet on a curve's shape, not its level
A maturity-aware graph model turns a tiny forecasting edge into a smooth, near-market-neutral return stream from commodity calendar spreads — correlation with the S&P 500 of about minus two-hundredths.
arXiv:2606.25811
Your uncertainty metric might be ranking models backwards
The standard ways we grade a model's confidence can be not just unhelpful but actively misleading — and the fix is to stop grading the forecast and start grading the decision it enables.
arXiv:2606.26990
In trading, a slow model is a useless model
In fast markets a mid-price signal decays in microseconds, so latency is part of the strategy — not an implementation detail. "Best model" is meaningless without a time budget.
arXiv:2606.25986
Three levers a serious engineering org pulls to get better
Correctness, infrastructure, culture. Jane Street, Slack and The Guardian each pulled a different lever this month — and together they show where lasting advantage hides when demos get cheap.
3 papers
When something is always breaking
Three teams — Cloudflare, Netflix and Airbnb — on three faces of staying reliable at scale: how to undo a half-finished job, schedule a flood of work fairly, and push changes to thousands of servers without breaking any.
3 papers
The error bars on rain are lying to you
Traditional weather uncertainty methods claim ninety percent confidence on rainfall but catch the truth only a third of the time. A distribution-free fix lands where forecasting begins.
arXiv:2606.27001
The leaderboard lie: foundation models top the rankings without finding alpha
Point a pretrained time-series model at the stock market and it wins almost every contest. Look closer and the gaps are a fraction of a single bit — a ranking victory that carries no edge you could trade.
arXiv:2606.27100
Forecast the easy bits, deal the rest downward
A retailer may need a billion product-by-store forecasts a week. This method predicts only the smooth 0.3% of them, then splits the rest with loaded dice so everything adds up.
arXiv:2606.26774
The one-line model that beats the Transformers
A line of algebra can match forecasting architectures thousands of times its size — if you stop scaling the model and start tuning the preprocessing nobody bothers to touch.
arXiv:2606.27282
Teaching a language model to actually hear a number
Language models shatter numbers into meaningless fragments before they ever reason about them. Fix that one interface — not the model — and forecasting accuracy jumps.
OpenReview preprint
Building a smarter eye to read a ball's spin
A camera that physically follows a ball in flight, cancels its travel, and reads the spin off the surface — live, on the regular ball, at 750 measurements a second.
arXiv preprint
The self-driving car that cried wolf
A popular way of training trajectory predictors quietly corrupts the probabilities a self-driving planner relies on. The fix needs no retraining — just a clearer view of what went wrong.
arXiv:2606.26424
The forecast is not the point: machine learning on the yield curve
Neural networks can beat the decades-old workhorses of bond forecasting — but this study insists on the harder test, asking whether a better forecast actually makes a better trade.
arXiv:2606.26815
The edge was never in the model
A machine-learning system can be genuinely right about Bitcoin's next move and still lose almost everything — because the cost of acting on each small correct call exceeds the call itself.
arXiv:2606.00060
Football's foundation-model moment
One reusable embedding of every on-ball event, learned BERT-style with the player names stripped out — and reused for expected goals, action value, and scouting.
arXiv:2606.09327
Elo was right by accident — here's the theory it stumbled onto
A sixty-year-old chess-rating trick turns out to be a special case of a clean statistical principle — one that extends naturally to draws, scorelines, and whole-field rankings, with fairness baked in.
arXiv:2604.09143
The marathon agents can't finish
Today's AI coding agents close ten-minute tickets with ease. Give them a forty-hour project — port Kubernetes, clone Slack — and the best of them fail seven times out of ten.
arXiv:2606.07682
When a confident forecast is lying to you
AI weather models are brilliant on average and quietly overconfident at the tails. A cheap, distribution-free correction makes their stated uncertainty match reality.
arXiv:2606.19642
Field notes: nine builds, three threads
From AIs that talk to each other in shorthand to a four-line fix after a six-week bug hunt — nine recent reads, and the threads that tie them together.
9 papers
From picking to making: the recommender that creates your feed
For decades feeds answered one question — of everything that exists, what should we show you? This vision argues the next question is what should we make for you.
arXiv:2304.03516
When machines stop writing for us
If the reader is another AI, why write in tidy English at all? A new method compresses text into dense, alien symbols that humans can't read but models still understand.
arXiv:2606.19857
PixelRAG: reading the web as pictures
Skip HTML parsing entirely — retrieve and read the web as screenshots, in pixel space, and beat text-based retrieval even on text-only questions.
PixelRAG paper (GitHub)
Asking versus enforcing: how to actually control an AI agent
An AI agent follows a written rule most of the time — but "most of the time" is exactly where reliability dies. The craft is knowing which rules to prompt and which to enforce in code.
Anthropic