Alex Bores, a Democrat from New York vying for a House seat, during a'Get Out The Vote' rally on the first day of early voting for a primary election in New York City. Alex Bores, a Democrat from New York vying for a House seat, during a'Get Out The Vote' rally on the first day of early voting for a primary election in New York City. New York City House primary emerges as key battleground in'AI civil war' T he artificial intelligence industry is spending heavily in the 2026 midterms, hoping to secure influence over the technology's first generation of legislation - and New York City's primary has emerged as the key battleground. AI-focused Super Pacs have raised over $100m this cycle, of which $49m has been spent so far, in dozens of congressional races across the country. Half of all spending has converged on a single Manhattan race: Tuesday's Democratic primary in the district of NY-12.

The race--whose candidates include Micah Lasher, Alex Bores, George Conway, and Jack Schlossberg--is at once glitzy, confusing, and uninspiring. Alex Bores is one of many candidates in the hotly contested race for New York's Twelfth Congressional district. A good seat in Congress can be hard to find, and difficult to get up from. The average district--and there are four hundred and thirty-five of them--is roughly the size of Wales, or New Jersey. New York's Twelfth District, which spans the Upper East Side, the Upper West Side, midtown, and Chelsea, is one of the richest, smallest, and most solidly Democratic districts in the country. It has the most people with college degrees and is in the ninety-fifth percentile for members of the Silent Generation. After its incumbent, Jerry Nadler, who has been in Congress since 1992, announced his retirement last year, the race to fill his seat has also become one of the most contested.

Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions. Traditionally BO has been set as a sequential decision-making process which estimates the utility of query points via an acquisition function and a prior over functions, such as a Gaussian process. Recently, however, a reformulation of BO via density-ratio estimation (BORE) allowed reinterpreting the acquisition function as a probabilistic binary classifier, removing the need for an explicit prior over functions and increasing scalability. In this paper, we present a theoretical analysis of BORE's regret and an extension of the algorithm with improved uncertainty estimates. We also show that BORE can be naturally extended to a batch optimisation setting by recasting the problem as approximate Bayesian inference. The resulting algorithms come equipped with theoretical performance guarantees and are assessed against other batch and sequential BO baselines in a series of experiments.

Andrew Cuomo and Donald Trump have both posted AI-generated videos on social media. Andrew Cuomo and Donald Trump have both posted AI-generated videos on social media. T he New York City mayoral election may be remembered for the remarkable win of a young democratic socialist, but it was also marked by something that is likely to permeate future elections: the use of AI-generated campaign videos. Andrew Cuomo, who lost to Zohran Mamdani in last week's election, took particular interest in sharing deepfake videos of his opponent, including one that saw the former governor accused of racism, in what is a developing area of electioneering. AI has been used by campaigns before, particularly in using algorithms to target certain voters, and even, in some cases, to write policy proposals.

Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions. Traditionally BO has been set as a sequential decision-making process which estimates the utility of query points via an acquisition function and a prior over functions, such as a Gaussian process. Recently, however, a reformulation of BO via density-ratio estimation (BORE) allowed reinterpreting the acquisition function as a probabilistic binary classifier, removing the need for an explicit prior over functions and increasing scalability. In this paper, we present a theoretical analysis of BORE's regret and

Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions. Traditionally BO has been set as a sequential decision-making process which estimates the utility of query points via an acquisition function and a prior over functions, such as a Gaussian process. Recently, however, a reformulation of BO via density-ratio estimation (BORE) allowed reinterpreting the acquisition function as a probabilistic binary classifier, removing the need for an explicit prior over functions and increasing scalability. In this paper, we present a theoretical analysis of BORE's regret and an extension of the algorithm with improved uncertainty estimates. We also show that BORE can be naturally extended to a batch optimisation setting by recasting the problem as approximate Bayesian inference.

Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions. Traditionally BO has been set as a sequential decision-making process which estimates the utility of query points via an acquisition function and a prior over functions, such as a Gaussian process. Recently, however, a reformulation of BO via density-ratio estimation (BORE) allowed reinterpreting the acquisition function as a probabilistic binary classifier, removing the need for an explicit prior over functions and increasing scalability. In this paper, we present a theoretical analysis of BORE's regret and an extension of the algorithm with improved uncertainty estimates. We also show that BORE can be naturally extended to a batch optimisation setting by recasting the problem as approximate Bayesian inference.