Utilizing mutual learning can effectively enhance the performance of peer BNNs.

The birds can make good pets, but only if taken care of properly. Breakthroughs, discoveries, and DIY tips sent six days a week. Rescuers in North Carolina recently saved over 500 pigeons from a home in Greensboro. Guildford County Animal Services and two other bird rescues based in Charlotte initially believed that the call was for about 300 birds . Instead, they found about 550 pigeons inside of a shed behind the home, hidden from the street.

A social network for AI looks disturbing, but it's not what you think A social network solely for AI - no humans allowed - has made headlines around the world. Chatbots are using it to discuss humans' diary entries, describe existential crises or even plot world domination . It looks like an alarming development in the rise of the machines - but all is not as it seems. Like any chatbots, the AI agents on Moltbook are just creating statistically plausible strings of words - there is no understanding, intent or intelligence. And in any case, there's plenty of evidence that much of what we can read on the site is actually written by humans.

West Midlands Police has admitted it overstated the evidence used to make the decision to ban Israeli fans from a match in Birmingham. Craig Guildford, its former chief constable, retired earlier this month after damning criticism of the ban on Maccabi Tel Aviv fans from the Europa League match against Aston Villa, last November. In newly released documents, the force also said we did not engage early enough with the local Jewish community, and indicated there was now a ban on AI use after its evidence included a match that did not take place. Furthermore, it said its operations would have lasted four days, involved multiple forces, and cost more than £5m, if 2,500 away fans had attended. The documents were released ahead of a public meeting on Tuesday, at which Police and Crime Commissioner for the West Midlands, Simon Foster, will discuss at his accountability and governance board, the decision to ban the Maccabi fans.

The chief constable of West Midlands Police has retired after damning criticism of a decision to ban Israeli fans from a match against Aston Villa. Craig Guildford's retirement was confirmed on Friday after both Downing Street and the home secretary said this week they had lost confidence in his leadership. He faced numerous calls to resign after apologising for providing incorrect evidence to MPs, which included the denial that AI was used in a report which led to the decision to ban Maccabi Tel Aviv fans from the game on 6 November. Announcing his retirement, Guildford, 52, did not offer an apology and blamed what he described as the political and media frenzy for his decision to step down. I have carefully considered my position and concluded that retirement is in the best interests of the organisation, myself and my family, he said.

Home Secretary Shabana Mahmood says she has lost confidence in West Midlands Police's chief constable after Israeli football fans were banned from a match against Aston Villa. Mahmood told MPs a damning review from the policing watchdog over the intelligence that led to Maccabi Tel Aviv fans being banned showed a failure of leadership. The force has apologised saying it did not deliberately distort evidence that was used by Birmingham's Safety Advisory Group for the 6 November game . Chief Constable Craig Guildford remains in post, but faces a meeting on 27 January to be questioned by Police and Crime Commissioner Simon Foster who has the authority to sack him. Mahmood told the Commons on Wednesday she intended to restore the power for home secretaries to dismiss chief constables who fail their communities.

When a police force is supposed to seek the truth and uphold the law, what happens when the evidence they present to officials and the public is, as Home Secretary Shabana Mahmood put it, exaggerated or untrue? The police inspectorate has concluded the leaders of West Midlands Police fell foul of confirmation bias. In simple terms, that means senior officers had already reached a decision and were looking for intelligence to justify it. The list of errors and inaccuracies set out in an independent review of the decision-making that led to fans of Israeli football club Maccabi Tel Aviv being banned from attending a fixture at Villa Park in November have been described by Mahmood as damning. They include: A report of a football match in an intelligence report produced using AI which never happened; a twice-repeated denial by senior police leaders to MPs that AI had not been relied on to produce the inaccurate report; the claim that local Jewish groups had been consulted on the move when they had not been; inaccurately presenting evidence from Dutch police reports from a previous fixture involving the club.

Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software development to customer support. However, LLM agents often underperform due to suboptimal configurations; poorly tuned prompts, tool descriptions, and parameters that typically require weeks of manual refinement. Existing optimization methods either are too complex for general use or treat components in isolation, missing critical interdependencies. We present ARTEMIS, a no-code evolutionary optimization platform that jointly optimizes agent configurations through semantically-aware genetic operators. Given only a benchmark script and natural language goals, ARTEMIS automatically discovers configurable components, extracts performance signals from execution logs, and evolves configurations without requiring architectural modifications. We evaluate ARTEMIS on four representative agent systems: the \emph{ALE Agent} for competitive programming on AtCoder Heuristic Contest, achieving a \textbf{$13.6\%$ improvement} in acceptance rate; the \emph{Mini-SWE Agent} for code optimization on SWE-Perf, with a statistically significant \textbf{10.1\% performance gain}; and the \emph{CrewAI Agent} for cost and mathematical reasoning on Math Odyssey, achieving a statistically significant \textbf{$36.9\%$ reduction} in the number of tokens required for evaluation. We also evaluate the \emph{MathTales-Teacher Agent} powered by a smaller open-source model (Qwen2.5-7B) on GSM8K primary-level mathematics problems, achieving a \textbf{22\% accuracy improvement} and demonstrating that ARTEMIS can optimize agents based on both commercial and local models.