标签：#prediction

Kalshi can't evade Nevada gambling laws by calling bets "swaps," judges rule.

The last post was about making a number trustworthy. Leakage geometry, purge widths, de-overlap, a baseline that could not cheat. It ended with a minute-scale ceiling that held at 52% across seven configurations and a model family swap. This one is about what happens after you trust the number. Because a probability you are going to bet on is a different object from a probability you are going to report. The probabilities are not decorative The path-passage classifier is a three-class LightGBM. It returns p_up , p_down , p_none . Those go straight into the expected-value score that decides whether to take a trade and how big: long_score = p_up * ( B - C ) + p_down * ( - B - C ) + p_none * ( - C ) short_score = p_up * ( - B - C ) + p_down * ( B - C ) + p_none * ( - C ) B is the barrier, C the cost. Read the arithmetic. Every term is linear in a probability. Scale p_up by 1.2 and you scale the long score by very nearly 1.2. So miscalibration does not stay in the model. It becomes a bet-sizing error, in proportion, in the bins where the gate actually fires. A classifier that is right 70% of the time while claiming 90% is not 20 points wrong. It is sizing every position in that bin as though the edge were far larger than it is. Boosted trees are known for uncalibrated softmax output. I had been consuming it as if it were a probability. The audit Seven live assets. For each one, fit an Inductive Venn-Abers wrapper on the time-ordered older 80% of that model's training data, 6,988 rows, and evaluate against a 500-row uniform-random sample of the newer 20%, seed 42. The LightGBM models are reloaded from disk and left alone. Only the wrapper is fit. Measure Expected Calibration Error and log-loss, before and after. Asset ECE before → after ECE Δ Log-loss Δ BTC 0.1272 → 0.0621 -51.2% -5.5% ETH 0.1795 → 0.0298 -83.4% -11.5% SOL 0.1680 → 0.0386 -77.0% -10.6% XRP 0.2219 → 0.0645 -70.9% -17.7% ADA 0.1419 → 0.0369 -74.0% -8.0% LINK 0.1260 → 0.0737 -41.5% -1.2% LTC 0.1508 → 0.0603

Dockerize Your LLM Proxy: One Container for Free Multi-Provider Access Want free LLM access in a repeatable, portable way? Run it as a container. Why Docker Single command to deploy anywhere Isolated environment with consistent deps Easy to put behind a reverse proxy DAVIL Cod in Docker DAVIL Cod ships a Dockerfile. Build and run with provider keys as env vars: docker build -t davil-cod . docker run -p 4000:4000 \ -e PROVIDER_GROQ_APIKEY = ... \ -e PROVIDER_MISTRAL_APIKEY = ... \ davil-cod Features you get Provider rotation with circuit breaker Disk cache for repeated prompts Dashboard on port 4000 FAQ Does it persist the cache? Yes — mount a volume for the cache directory. Can I expose it to my team? Yes — it's a normal HTTP service with token auth.

Have we tried turning off society and turning it back on again?

From threats to the safety of poll workers to voters who can’t distinguish between odds and results, prediction markets are already scrambling the political process.

Kalshi ordered to stop offering bets in Washington, must implement geofencing.

Jacob Fortinsky, the CEO and cofounder of the new prediction market Novig, says his outfit isn’t like those other markets. You know the ones.

Trump admin claims New York suing Kalshi created "market emergency."

FlightAware says that Kalshi used its name and data to offer bets on flight cancellations without the flight tracker's permission.

Fire experts warn such markets could incentivize arson.

Judge may allow Minnesota to ban some types of bets, but not all of them.

The prediction market’s Panamanian operation seems odd, even for a company whose CEO had his apartment raided by FBI agents.

If only someone could have predicted it.

One of Kalshi’s most prominent traders tells WIRED he’s swearing off Spotify-related markets until the issue is resolved.

"Winning" bets were made on cloned website and would have lost money, WSJ finds.

Getting the future right is now big business. But at a festival in Berkeley, forecasters worry that sports markets could take the whole industry down.

description: While most people chase political bets, these traders are dominating daily temperature...

description: Weather markets on Polymarket have become one of the hottest and most consistent...

It’s the first estimate of how many Americans are sneaking onto Polymarket’s banned crypto-based platform.

Social media posts questioning the integrity of LA’s mayoral election were labeled “paid partnerships.” Then Kalshi and Polymarket told creators to delete them.