We introduce a family of chronologically consistent, instruction-tuned large language models to eliminate lookahead bias. Each model is trained only on data available before a clearly defined knowledge-cutoff date, ensuring strict temporal separation from any post-cutoff data. The resulting framework offers (i) a simple, conversational chat interface, (ii) fully open, fixed model weights that guarantee replicability, and (iii) a conservative lower bound on forecast accuracy, isolating the share of predictability that survives once training leakage is removed. Together, these features provide researchers with an easy-to-use generative AI tool useful for a wide range of prediction tasks that is free of lookahead bias.

A key challenge in transportation planning is that the collective preferences of heterogeneous travelers often diverge from the policies produced by model-driven decision tools. This misalignment frequently results in implementation delays or failures. Here, we investigate whether large language models (LLMs)--noted for their capabilities in reasoning and simulating human decision-making--can help inform and address this alignment problem. We develop a multi-agent simulation in which LLMs, acting as agents representing residents from different communities in a city, participate in a referendum on a set of transit policy proposals. Using chain-of-thought reasoning, LLM agents provide Ranked-Choice or approval-based preferences, which are aggregated using instant-runoff voting (IRV) to model democratic consensus. We implement this simulation framework with both GPT-4o and Claude-3.5, and apply it for Chicago and Houston. Our findings suggest that LLM agents are capable of approximating plausible collective preferences and responding to local context, while also displaying model-specific behavioral biases and modest divergences from optimization-based benchmarks. These capabilities underscore both promise and limitations of LLMs as tools for solving the alignment problem in transportation decision-making. Introduction Urban transportation policy plays a central role in shaping regional development. Designing effective policy requires access to multidimensional data and a deep understanding of individual preferences across heterogeneous communities. Conventional approaches typically rely on structured mathematical models that identify an optimal policy under specified objectives and constraints. However, these models often rest on rigid assumptions and oversimplified behavioral representations. As a result, they may produce solutions that are analytically tractable yet poorly aligned with public sentiment or the complex realities of policy implementation. This misalignment frequently contributes to delays--or even failures--in policy approval and execution. Trained on vast corpora of text encompassing news, facts, and human discourse, LLMs possess a rich contextual understanding that could potentially help policymakers infer public preferences and explore trade-offs before implementation. Their ability to interpret unstructured information, reason about competing objectives in natural language, and adapt to specific contexts suggests a new form of decision support that complements the traditional paradigm. In this study, we implement a multi-agent voting framework to examine the potential of LLMs in supporting transportation policy design.

What exactly tipped the Brexit referendum in the favour of the Leave campaign on voting day – June 23, 2016 – may never been clear cut. But a new study suggests the intelligence of voters – and their susceptibility to being duped by misinformation – played a part. From a sample of Brits, researchers looked at how exactly they voted, as well as their intelligence, as determined by performance in cognitive tasks. They found a link between high performance in the tasks and voting Remain, which suggests people who wanted to stay in the EU have higher intelligence. However, the study method only looked at data from just over 6,000 referendum voters – a far cry from the 33.5 million who cast their ballot that day.

Russia's defence ministry has said its air defence forces destroyed a large-scale Ukrainian-launched drone attack on the Crimean Peninsula, which Moscow annexed from Ukraine in 2014. Crimea has been targeted by Kyiv since Moscow launched its full-scale invasion of Ukraine in February 2022, but has come under more intense, increased attacks in recent weeks. The Russian Ministry of Defence said early on Friday its forces shot down nine drones, while 33 others "were suppressed by electronic warfare and crashed without reaching the target". It did not elaborate on whether there had been any damage or casualties. It added that it had also shot down a Ukraine-launched missile over the Kaluga region, which borders the Moscow region.

The Kremlin said Thursday that the Moscow-annexed Crimean Peninsula was vulnerable to Ukrainian attacks after officials said they had shot down a drone near a key naval base. The latest drone attack comes after Russian President Vladimir Putin recently visited the only bridge connecting Crimea with the Russian mainland to survey work to repair the key artery damaged in a blast Moscow blamed on Kiyv. "There are certainly risks because the Ukrainian side continues its policy of organising terrorist attacks. But, on the other hand, information we get indicates that effective countermeasures are being taken," Kremlin spokesman Dmitry Peskov told reporters. The Moscow-appointed governor of Crimea Sergei Aksyonov said last month that Russia was strengthening fortifications on the peninsula in the wake of recent attacks.

Oliver Letwin's strange and somewhat alarming new book begins at midnight on Thursday 31 December 2037. In Swindon – stay with me! – a man called Aameen Patel is working the graveyard shift at Highways England's traffic HQ when his computer screen goes blank, and the room is plunged into darkness. He tries to report these things to his superiors, but can get no signal on his mobile. Looking at the motorway from the viewing window by his desk, he observes, not an orderly stream of traffic, but a dramatic pile-up of crashed cars and lorries – at which point he realises something is seriously amiss. In the Britain of 2037, everything, or almost everything, is controlled by 7G wireless technology, from the national grid to the traffic (not only are cars driverless; a vehicle cannot even join a motorway without logging into an "on-route guidance system"). There is, then, only one possible explanation: the entire 7G network must have gone down. It sounds like I'm describing a novel – and it's true that Aameen Patel will soon be joined by another fictional creation in the form of Bill Donoghue, who works at the Bank of England, and whose job it will be to tell the prime minister that the country is about to pay a heavy price for its cashless economy, given that even essential purchases will not be possible until the network is back up (Bill's mother-in-law is also one of thousands of vulnerable people whose carers will soon be unable to get to them, the batteries in their electric cars having gone flat).

The House of Commons will vote next week on Theresa May's amended Brexit deal. Ahead of this, MPs are beginning to submit their own amendments. Among the proposals so far are those aimed at: preventing a no-deal Brexit; extending the Article 50 deadline if a deal isn't agreed by 26 February; looking at options including renegotiating with Brussels or holding another referendum. On Monday, the prime minister said she was focusing on altering the Irish backstop, and that she was scrapping proposals for a £65 fee for EU citizens to remain in the UK. But Labour's Jeremy Corbyn argued that Mrs May was in denial about the level of opposition to her plans.

The new long-term NHS spending proposals which are published on Monday make many of the front pages. The Daily Telegraph says the 10-year plan will see every child with cancer offered genetic testing so they can receive more effective, personalised treatment. It reports that the government hopes the overall plan will save 500,000 lives - a figure that is also splashed on the front pages of the Daily Express and the Daily Mail. New technology is at the heart of the government's healthcare plan, the i newspaper says, and artificial intelligence will also be used to prevent "major killer conditions" in the coming years. The Mail features a piece written by Chancellor Philip Hammond, in which he says the NHS must improve efficiency to ensure the extra cash - a £20.5bn a year funding boost by 2023/24 - is not wasted.

Robots, though a tiny fraction of the workforce, are seeing rapid growth around the world. Though the global average of robots in the factory workforce is one robot for 150 humans, in South Korea, there is a robot for every 20 humans in the manufacturing workforce. The robot to human work ratio in manufacturing around the world is definitely on a rise. As the number of robots working grows, the cost of maintaining robots will also decrease along with the cost of making robots, creating a snowball effect, meaning the number of robots will be rising. In the coming decades, it is predicted over half of the jobs being done by humans will be automated.

The head of the NHS in England, Simon Stevens, is in the news this morning. According to the Times, five million patients a month are waiting more than three weeks to see their GP. And the paper says 1,000 fewer family doctors are in post than when ministers pledged to recruit an extra 5,000 in 2015. Mr Stevens' plan for joined up care to keep patients out of hospital "relies on beefed-up GP surgeries offering more treatment and co-ordination locally, but despite extra money, £20,000 'golden hellos' and overseas recruitment drives, numbers continue to fall", the Times adds. Meanwhile, Mr Stevens is said to be at loggerheads with Downing Street, the Treasury and Department of Health and Social Care about how much his long-term plan for the health service can promise to boost care.