Explore how utilizing Adobe Firefly and AI-powered features in Premiere Pro and After Effects can elevate your creation of standout video content for social media. Join award-winning editor and producer Karina Anglada as she guides you through several techniques, tips, and tricks to expand the creative possibilities of working with social video content. You’ll learn how to: Level up your content with generative AI and the Firefly Video Model Take advantage of AI-powered features to optimize your video content for better engagement and performance on social media Subscribe to Adobe Creative Cloud: https://adobe.ly/48Y1QJ1 Learn more about Creative Cloud: https://adobe.ly/3RTndnp About Adobe Creative Cloud: Unlocking creative potential goes beyond tools – it's about cultivating inspiration, fostering innovation, and mastering artistic expression. On the Adobe Creative Cloud YouTube channel, discover stories, concepts, and trends that ignite your creativity. We are your hub for creativity, connecting you with Adobe channels for detailed tutorials and product insights. Adobe® Creative Cloud™ brings together everything you need to create your greatest work. One membership gives you access to all Adobe professional creative desktop applications, plus new features as soon as they're available. Cloud storage ensures file access anywhere, even on mobile, streamlining concept sharing. Cloud-based services let you build websites, mobile apps, and content for any medium/device. With Behance integration, you can publish your portfolio on your own URL and plug into the world's largest creative community to get inspired, get feedback, and find new opportunities. Connect with Adobe Creative Cloud: Twitter: https://twitter.com/creativecloud LinkedIn: https://www.linkedin.com/showcase/adobe-creative-cloud/ Facebook: https://www.facebook.com/adobecreativecloud Instagram: https://www.instagram.com/adobecreativecloud/ #Adobe #AdobeYouTube #AdobeCreativeCloud

Both Canada and the United States have deep-seated affordability problems, but only the former is doing anything substantial about it. Forthcoming housing cooperatives at 2444 Eglinton Avenue in Toronto, and in Upper Hammonds Plains, Nova Scotia, are helping put a dent in Canada’s affordable housing shortage. Vancouver’s home prices today are close to $1 million, and rental prices in Toronto are equally astronomical. To buck this trend, Canada’s Co-operative Housing Development Program (CHDP) unlocked $1.5 billion in federal financing to support new cooperative housing. This is all happening as part of Canada’s National Housing Strategy, a $115 billion plan to boost affordability.  “In Toronto, the housing crisis is as severe as it’s ever been,” UT Daniels professor Keisha St. Louis-McBurnie, a Toronto-based urban planner at Monumental, told AN.  “We’ve seen real growth in housing encampments, especially during COVID-19,” St. Louis-McBurnie said. “There’s been very limited new transitional and supportive housing across [Toronto]. Households are getting priced out of the market, including professional middle-income ones. Folks who are low-income that require the most housing support are not able to access new affordable housing, especially in consideration to what’s getting built in Toronto.” A Brutalist housing co-op on Eglinton Avenue in Toronto (Ken Lund/Flickr/CC BY 2.0) Claire Weisz’s office, WXY, as of this year has locations in New York and Toronto. Weisz recently spoke at the Canadian Club Toronto, in a round table moderated by Alex Bozikovic, about urbanism. “Huge troves of affordable housing in New York has, in recent years, been taken from people who can’t afford down payments on co-ops,” Weisz told AN. “We’ve sacrificed so much. Some organizations have tried to stop this, but without policy support from the city, it’s really in vain.” “My big worry is that right now, like Toronto, New York is starting to be like the rest of the U.S. and rely on developer-led for-profits, versus not-for-profits,” Weisz added. “There needs to be a reawakening of not-for-profit development coalitions.” “The Co-operative Housing Sector is Booming” The Canadian National Housing Strategy’s longterm goal is to build 156,000 affordable units and repair over 298,000 existing ones. Housing cooperatives are getting built all over Canada as part of the program, from British Columbia, Ontario, and Nova Scotia. Planning departments are prioritizing the needs of First Nations communities and Black Canadians to help rectify past injustices. This is happening as rent prices skyrocket, and Toronto’s skyline is populated with new landmarks by Frank Gehry, Studio Gang, BIG, and others. Cooperative housing was first built in Canada in the 1930s. Regent Park in Toronto was the country’s first public housing campus, finished in 1949. This legacy continued through the 1960s and ’70s, when radical co-ops like Rochdale College and Neill-Wycik were built for University of Toronto students. Willow Park Housing Co-op (1966) went up in Winnipeg thanks to CHF Canada, a joint initiative by the Canadian Labour Congress and the Co-operative Union of Canada. The New Democratic Party (NDP) constructed abundant cooperative housing in Vancouver. Milton Park got built in Montreal in the 1980s. Between 1973 and 1993, CHF Canada built a total 92,000 cooperatively-owned units. (This history was captured by Leslie Coles in Under Construction: A History of Co-operative Housing in Canada.) All this momentum was brought to a halt during successive Brian Mulroney and Jean Chrétien Premierships, however, when government support for supportive housing was cut, much like what was happening in the U.S. at that time under the Clinton administration with the Faircloth Amendment. Regent Park’s original architecture was demolished in 2005 as part of the Regent Park Revitalization Plan, and replaced with a private, mixed-income community. (Kevin Costain/Wikimedia Commons /CC BY 2.0) A regime of state-imposed austerity ensued, leading up to the affordability crisis both Canada and the U.S. have today. Unlike the United States, however, Canada seems to have learned from its past mistakes. Thanks to Canada’s Co-operative Housing Development Program, eight co-ops are getting built right now. Toronto Mayor Olivia Chow has prioritized new affordable housing construction and land trusts, and is doing much to fight gentrification. BC Builds is an initiative helping fast track cooperative housing in Vancouver City Council. “Since the 1990s there’s been a shift in liberal to conservative and neoliberal federal governments,” St. Louis-McBurnie said. “This resulted in reduced public investment in significant social programs, including public and not-for-profit housing. These successive governments devolved responsibility for funding affordable housing to provincial governments across the country, Ontario in particular. Places like Regent Park now have a public-private partnership model, meaning it’s now on the private market. Alexandra Park is going through a similar privatization process.” “But now, there’s interest in alternatives” to market rate development St. Louis-McBurnie affirmed, “and the co-operative housing sector is booming.” Provinces and cities are also implementing “communal land trust models to support the scaling and retaining of assets,” she said. “They’re trying to figure out ways for bringing independently-owned co-ops into the land trust model.” Housing as Human Right The largest co-op underway in Canada today is 2444 Eglinton Avenue by Henriquez Partners and Claude Cormier + Associés. The Toronto development will yield 918 homes, including 612 affordable, rent-geared-to-income (RGI) units. Retail offerings will be sited at the base level. From afar, 2444 Eglinton Avenue will stand out thanks to its polychromatic porthole windows. Further afield in Perth, Ontario, 38 new cooperative units will be built. Farther east in Upper Hammonds Plains, Nova Scotia, a co-operative housing development will yield 136 row house units primarily for Black Canadians. That project is happening through a partnership between the Upper Hammonds Plains Community Land Trust and the Upper Hammonds Plains Housing Co-operative. Curtis Whiley, a sixth-generation African Nova Scotian, is steering the housing cooperative project in Upper Hammonds. Meanwhile in New Minas, Nova Scotia, there will be 32 more cooperative homes. Rendering of 2444 Eglinton Avenue Co-ops (Courtesy Henriquez Partners) Africville was a close-knit Black community in Halifax located on Treat 1 territory destroyed by the City of Halifax in the 1960s. Today, land trusts like the one in Nova Scotia are effective means for establishing housing secure communities of color. The Toronto Chinatown Land Trust likewise empowers people to stay in place, an outfit helmed by Chiyi Tam who is a planner and UT Daniels faculty member. “We have not seen any investment like this, I would say, in terms of housing development almost exclusively for Black communities in Canada’s history,” St. Louis-McBurnie said. Hogan’s Alley’s Black community was displaced by the Vancouver government to make way for the Georgia and Dunsmuir viaducts in 1971. Now, members of the NDP and Hogan’s Alley Society—a Black-led, not-for-profit developer of Afrocentric affordable housing—are working together to shore up Black land stewardship in the old neighborhood and help rectify the past injustice. “Transferring land over to the Hogan Alley land trust will allow for the Black community to return and for greater autonomy in housing construction,” St. Louis-McBurnie added. “What If We Built a New Co-op City in Brooklyn?” Federal spending was allocated in the Biden administration’s Infrastructure Investment and Jobs Act, or the Bipartisan Infrastructure Law, to dismantle highways that ripped through inner cities and destroyed African American neighborhoods, like I-81 in Syracuse, New York. But this week, House GOP members moved to cancel the I-81 highway removal project. The Trump administration’s proposed 2026 national budget has slashed spending on projects that “fall outside [the President’s] new priorities” and “promote radical equity policies,” the White House said. Is it possible for architects, politicians, and planners in the U.S. to replicate Canada’s success given the current political climate?  It seems, for now, it would have to happen with aggressive leadership at the city and state levels—trade unions and nonprofits would also have to step up. This is already taking place, for instance, at Penn South, a sprawling Mitchell-Lama housing cooperative in Manhattan by the United Housing Foundation (UHF). Today, Bernheimer Architecture (BA) and the AFL-CIO Housing Investment Trust are helping upgrade the handsome midcentury campus. Penn South’s rehabilitation is in conjunction with BA, the AFL-CIO, and the New York State Energy Research and Development Authority (NYSERDA). “Penn South is a very unique campus, and its needs are different from most other campuses in New York City,” Andy Bernheimer told AN. “NYSERDA is helping us inform design and construction moving forward, which will entail reskinning the buildings and making them more energy efficient.” Co-op City is situated on a sprawling 320-acre site in the north Bronx. (Zara Pfeifer) Co-op City shopping plaza (Zara Pfeifer) In New York today, mayoral candidates are increasingly interested in revisiting the Mitchell-Lama Program’s success, a UHF campaign that built 135,000 cooperative housing units between 1955 and 1978, like Penn South and the Bronx’s Co-op City, another historic campus by Herman Jessor. In Albany, New York State elected officials have proposed a new Social Housing Development Authority, which would allocate government spending toward public housing, co-ops, and land trusts to battle gentrification. “I don’t think there’s enough money to simply restart a program like Mitchell-Lama, as far as I can tell,” Weisz told AN. “But if you look at all of the older Mitchell-Lamas flipping to the market, it’s clear we need to preserve the ones that are left, and there needs to be a new generation of co-ops. All over the city, when people have to pay market rates instead of mortgages, they’re rent burdened.” Homes for Living is a new book by Jonathan Tarleton that speaks to the tumultuous privatization of New York’s cooperative housing stock, a burgeoning problem. “Maybe there’s a way to build a funding and oversight mechanism for existing co-ops worried about going under water, and for households to sign up for a program that helps them to stay in [Mitchell-Lama],” Weisz elaborated. “Maybe there could even be a program for rental apartments to get into that program?” WXY is currently working on a Mitchell-Lama campus in the Bronx, Stevenson Commons, together with Habitat for Humanity. The goal is to maintain Stevenson Common’s affordability with rent-stabilized flats at very low rates. Parking lots at Stevenson Commons were rezoned to allow for new housing, which helps maintain affordability, while new public spaces and tennis clubs were added. There will be incentives to help seniors age in place, and for multigenerational households. Rochdale Village in Queens (Zara Pfeifer) Weisz sees opportunities to finance cooperative housing with ulterior means, like capital raised from Habitat for Humanity, but also congestion pricing. “We should be using new lines and TOD to actually support neighborhoods and co-ops, and people that are ultimately the ones who stay and support neighborhoods,” she said. “Why not subsidize co-op structures? The only way to do that is if there’s city-owned land, because, otherwise, the land cost is so expensive, you have to develop it at market rate.” “There’s a lot of city sites that have been identified for housing,” Weisz noted. “There’s all sorts of sites in the city’s hands right beside the Manhattan Bridge, for instance, or along the BQE. All of those sites could become new co-ops. What if we built a new Co-op City in Brooklyn?”

Marvel Rivals developer NetEase has announced some good--and bad--news for cosmetic completionists, as the studio is considering bringing back older battle passes to the game, albeit at a higher price. The Season 0 battle pass that will be available to purchase once again starting May 15 when the Galacta's Gift event begins, but instead of paying 490 Lattice for it, the price has now increased to 590 Lattice.The battle pass will also be available until May 29, but once purchased, the rewards contained in it can be unlocked at your leisure. In terms of price, this works out to roughly $7 for the battle pass if you don't have any of the premium in-game currency saved up. NetEase added that it is considering bringing older battle passes back in the future, but these will cost at least 20% more. There'll be no free rewards in these limited-time battle passes either, as NetEase noted that access to all rewards will require the purchase of the Luxury Battle Pass."Future Battle Pass returns might occur, but any such plans will span at least two seasons and be priced at a minimum of 20% higher than the original seasonal rate," the studio said in a blog post.Continue Reading at GameSpot

Join Tony Harmer for an energetic, fast-paced session that reveals the powerful capabilities of Illustrator that most users never discover. Learn the essential techniques and hidden features that separate novice users from true professionals, as Tony demonstrates how to dramatically accelerate your workflow and achieve accurate results. This session cuts through the basics to focus on game-changing techniques that will transform your approach to vector workflows, allowing you to tackle complex projects with speed and precision. This session will cover: Advanced transformation techniques for ultra-fine control and rapid iteration Power-user methods for making lightning-fast adjustments across complex designs Professional techniques for precise object manipulation in complex artwork Advanced attribute-stacking and styling techniques for sophisticated effects Time-saving tools and shortcuts that streamline complex tasks Subscribe to Adobe Creative Cloud: https://adobe.ly/48Y1QJ1 Learn more about Creative Cloud: https://adobe.ly/3RTndnp About Adobe Creative Cloud: Unlocking creative potential goes beyond tools – it's about cultivating inspiration, fostering innovation, and mastering artistic expression. On the Adobe Creative Cloud YouTube channel, discover stories, concepts, and trends that ignite your creativity. We are your hub for creativity, connecting you with Adobe channels for detailed tutorials and product insights. Adobe® Creative Cloud™ brings together everything you need to create your greatest work. One membership gives you access to all Adobe professional creative desktop applications, plus new features as soon as they're available. Cloud storage ensures file access anywhere, even on mobile, streamlining concept sharing. Cloud-based services let you build websites, mobile apps, and content for any medium/device. With Behance integration, you can publish your portfolio on your own URL and plug into the world's largest creative community to get inspired, get feedback, and find new opportunities. Connect with Adobe Creative Cloud: Twitter: https://twitter.com/creativecloud LinkedIn: https://www.linkedin.com/showcase/adobe-creative-cloud/ Facebook: https://www.facebook.com/adobecreativecloud Instagram: https://www.instagram.com/adobecreativecloud/ #Adobe #AdobeYouTube #AdobeCreativeCloud

Author(s): Marie Originally published on Towards AI. Hallucinations in Healthcare LLMs: Why They Happen and How to Prevent Them Building Trustworthy Healthcare LLM Systems — Part 1 Image generated by the author using ChatGPT TL;DR LLM hallucinations: AI-generated outputs that sound convincing but contain factual errors or fabricated information — posing serious safety risks in healthcare settings. Three main types of hallucinations: factual errors (recommending antibiotics for viral infections), fabrications (inventing non-existent studies or guidelines), misinterpretations (drawing incorrect conclusions from real data). Root causes of hallucinations: probabilistic generation, training that rewards fluency over factual accuracy, lack of real-time verification, and stale or biased data. Mitigation approaches: Retrieval-Augmented Generation (RAG), domain-specific fine-tuning, advanced prompting, guardrails. This series: build a hallucination-resistant pipeline for infectious disease knowledge, starting with a PubMed Central corpus. Hallucinations in medical LLMs aren’t just bugs — they’re safety risks. This series walks through how to ground healthcare language models in real evidence, starting with infectious diseases. Introduction LLMs (large language models) are changing how we interact with medical knowledge — summarizing research, answering clinical questions, even offering second opinions. But they still hallucinate — and in medicine that’s a safety risk, not a quirk. In medical domains, trust is non-negotiable. A hallucinated answer about infectious disease management (e.g., wrong antibiotic, incorrect diagnostic criteria) can directly impact patient safety, so grounding models in verifiable evidence is mandatory. That’s why this blog series exists. This four-part series will show you how to build a hallucination-resistant workflow, step-by-step: Part 1 (this post): what hallucinations are, why they happen and how to build a domain-specific corpus using open access medical literature Part 2: Turn that corpus into a RAG pipeline Part 3: Add hallucination detection metrics Part 4: Put it all together and build a transparent interface to show users the evidence behind the LLM’s responses What Are Hallucinations in LLMs? Hallucinations are model-generated outputs that sound correct and coherent, but are not factually correct. They sound convincing but are often false, unverifiable or entirely made up. Why They Matter in Healthcare These errors can have serious implications, especially in clinical settings where they might lead to improper treatment recommendations. The wrong recommendation in clinical settings could have life or death consequences, which is why it is critical to mitigate these hallucinations by building transparent, evidence-based systems. Image generated by the author using ChatGPT Main Types of Hallucinations 1. Factual Errors Factual errors happen when LLMs make incorrect claims about verifiable facts. Using our infectious disease example, recommending antibiotics for influenza would be a type of factual error. 2. Fabrications Fabrications involve LLMs inventing non-existent entities or information. In the context of healthcare, for example, these could be fictional research studies, medical guidelines that don’t exist or made-up technical concepts. 3. Misinterpretations Misinterpretation happens when LLMs take real information but misrepresents or mis-contextualizes it. For example, a model might reference a study that exists, but draws the wrong conclusions Why LLMs hallucinate Large language models hallucinate because they don’t truly understand facts like humans do simply predict what words should come next based on patterns they’ve observed in their training data. When these AI systems encounter unfamiliar topics or ambiguous questions, they don’t have the ability to say “I don’t know” and instead generate confident-sounding but potentially incorrect responses. This tendency stems from several factors: Their training prioritizes fluent, human-like text over factual caution They lack real-time access to verified information sources They have no inherent understanding of truth versus fiction. Conflicting information in training data can push the model to average contradictory sources. The problem is compounded by limitations in training data that may contain outdated, biased, or inaccurate information, as well as the fundamental auto-regressive nature of how these models generate text one piece at a time. How Can We Address Hallucinations? There are various methods to mitigate or detect hallucinations. Mitigation Strategies Fine-tuning with Domain-Specific Data: The main reason for hallucination lies in knowledge gaps in the model’s training data. This approach helps by introducing domain specific knowledge and can be very powerful to create models that understand better the specialized medical terminology or various nuances in clinical text. Retrieval-Augmented Generation (RAG): This method allows the integration of external knowledge sources by retrieving relevant information before generating the answer. It helps by grounding the model outputs in verified external sources instead of relying only on the model’s training data. This is the method we will be focusing on in this series Other noteworthy strategies: advanced prompting methods like Chain-of-Thoughts or Few-Shot Learning can help mitigate hallucinations by guiding the model’s answer in the right direction. Rules-based guardrails that screen outputs before they reach users add another safety layer. Hallucination Detection Source-attribution scoring: This method compares the LLM answer to the retrieved documents to detect how much of the answer is grounded in the source. Beyond identifying hallucinations, it also allows to highlight the source behind the LLM answer, which helps building trust and transparency. Semantic Entropy Measurement: This method measures uncertainty about the meaning of generated responses and has been developed specifically to address the risk of hallucinations in critical areas involving patient safety for example Consistency-Based Methods: This method involves a self-consistency check, where hallucinations can be detected by prompting the model multiple times with the same query and comparing the outputs for consistency. Some interesting open-access publications to go a bit further: If you’re interesting in reading recent research on this topic, here’s a few research papers worth reading: Code Walkthrough: Downloading Medical Research from PubMed Central To reduce hallucinations in healthcare LLMs, grounding them in reliable medical literature is critical. Let’s start by building a corpus from one of the best sources available: PubMed Central (PMC). This script helps you automate the retrieval of open-access medical papers, making it easy to bootstrap a dataset tailored to your task (e.g., infectious diseases). Here’s how it works: 1. Setup and Environment import requestsimport xml.etree.ElementTree as ETimport jsonimport os, re, timefrom dotenv import load_dotenvload_dotenv()api_key = os.getenv("NCBI_API_KEY")email = os.getenv("EMAIL")base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/" You’ll need to set your NCBI API key and email in a .env file. You can still call the NCBI API without an API key, but this unlocks higher rate limits and it is free 2. Search PMC Because we are interested in full texts to build our knowledge base, we should only download articles that are open access. To do so, we need to fetch the articles from PMC: # 1. Search PMCsearch_url = f"{base_url}esearch.fcgi"search_params = { "db": "pmc", "term": query, "retmax": max_results, "retmode": "json", "api_key": api_key, "email": email}print("Searching PMC...")search_resp = requests.get(search_url, params=search_params)search_resp.raise_for_status()ids = search_resp.json()["esearchresult"]["idlist"] This code queries PMC with your search terms (for example “infectious diseases”) and returns a list of document identifiers (PMCIDs). 3. Fetch and Parse Articles Now we can fetch the full texts using the PMCIDs: # 2. Batch fetchfetch_url = f"{base_url}efetch.fcgi"for i in range(0, len(ids), batch_size): = ids[i : i + batch_size] batch_ids fetch_params = { "db": "pmc", "id": ",".join(batch_ids), "retmode": "xml", "api_key": api_key, "email": email, } time.sleep(delay) r = requests.get(fetch_url, params=fetch_params) r.raise_for_status() Our response is an XML object, so the final step is to parse it and create a dictionary with the relevant sections: pmcid, title, abstract, full_text, publication_date, authors: root = ET.fromstring(r.content)for idx, article in enumerate(root.findall(".//article")): # Extract article details article_data = { "pmcid": f"PMC{batch_ids[idx]}", "title": "", "abstract": "", "full_text": "", "publication_date": "", "authors": [], } # Extract title title_elem = article.find(".//article-title") if title_elem is not None: article_data["title"] = "".join(title_elem.itertext()).strip() # Extract abstract abstract_parts = article.findall(".//abstract//p") if abstract_parts: article_data["abstract"] = " ".join( "".join(p.itertext()).strip() for p in abstract_parts ) # Extract publication date pub_date = article.find(".//pub-date") if pub_date is not None: year = pub_date.find("year") month = pub_date.find("month") day = pub_date.find("day") date_parts = [] if year is not None: date_parts.append(year.text) if month is not None: date_parts.append(month.text) if day is not None: date_parts.append(day.text) article_data["publication_date"] = "-".join(date_parts) # Extract authors author_elems = article.findall(".//contrib[@contrib-type='author']") for author_elem in author_elems: surname = author_elem.find(".//surname") given_names = author_elem.find(".//given-names") author = {} if surname is not None: author["surname"] = surname.text if given_names is not None: author["given_names"] = given_names.text if author: article_data["authors"].append(author) # Extract full text (combining all paragraphs) body = article.find(".//body") if body is not None: paragraphs = body.findall(".//p") article_data["full_text"] = " ".join( "".join(p.itertext()).strip() for p in paragraphs ) The data can then be saved into a jsonl that will be used in our next step — building our RAG system. Let’s be mindful of licensing restrictions: While open access literature allows anyone to access and read the content, it doesn’t mean the authors agreed to redistribution of their work. While this blog post and its content are intended for personal and educational use, if you decide to use this function to build a dataset that will be redistributed or commercialized, it is important to comply with the article’s license agreement. To do so, let’s define a function that will help us pull the license data from the downloaded article: def detect_cc_license(lic_elem): """ Inspect <license> … </license> for Creative Commons URLs or keywords and return a normalised string such as 'cc-by', 'cc-by-nc', 'cc0', or 'other'. """ if lic_elem is None: return "other" # 1) gather candidate strings: any ext-link href + full text candidates: list[str] = [] for link in lic_elem.findall(".//ext-link[@ext-link-type='uri']"): href = link.get("{http://www.w3.org/1999/xlink}href") or link.get("href") if href: candidates.append(href.lower()) candidates.append("".join(lic_elem.itertext()).lower()) # 2) search for CC patterns for text in candidates: if "creativecommons.org" not in text and "publicdomain" not in text: continue # order matters (most restrictive first) if re.search(r"by[-_]nc[-_]nd", text): return "cc-by-nc-nd" if re.search(r"by[-_]nc[-_]sa", text): return "cc-by-nc-sa" if re.search(r"by[-_]nc", text): return "cc-by-nc" if re.search(r"by[-_]sa", text): return "cc-by-sa" if "/by/" in text: return "cc-by" if "publicdomain/zero" in text or "cc0" in text or "public domain" in text: return "cc0" return "other" Here’s a short breakdown of what the licenses mean: Image uploaded by author Here’s the full function for PubMed download: def download_pmc_articles(query, ): max_results = 100, batch_size = 20, delay = 0.2, allowed_licenses = {"cc-by", "cc-by-sa", "cc0"}, out_file = "pmc_articles.jsonl" base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/" # 1. Search PMC search_url = f"{base_url}esearch.fcgi" search_params = { "db": "pmc", "term": query, "retmax": max_results, "retmode": "json", "api_key": api_key, "email": email } print("Searching PMC...") search_resp = requests.get(search_url, params=search_params) search_resp.raise_for_status() ids = search_resp.json()["esearchresult"]["idlist"] # 2. Batch fetch fetch_url = f"{base_url}efetch.fcgi" skipped, saved = 0, 0 with open(out_file, "w") as f: for i in range(0, len(ids), batch_size): batch_ids = ids[i:i+batch_size] fetch_params = { "db": "pmc", "id": ",".join(batch_ids), "retmode": "xml", "api_key": api_key, "email": email } time.sleep(delay) r = requests.get(fetch_url, params=fetch_params) r.raise_for_status() root = ET.fromstring(r.content) for idx, article in enumerate(root.findall(".//article")): # Check license license = detect_cc_license(article.find(".//license")) if license not in allowed_licenses: skipped += 1 continue # skip disallowed license # Extract article details article_data = { "pmcid": f"PMC{batch_ids[idx]}", "title": "", "abstract": "", "full_text": "", "publication_date": "", "authors": [] } # Extract title title_elem = article.find(".//article-title") if title_elem is not None: article_data["title"] = "".join(title_elem.itertext()).strip() # Extract abstract abstract_parts = article.findall(".//abstract//p") if abstract_parts: article_data["abstract"] = " ".join("".join(p.itertext()).strip() for p in abstract_parts) # Extract publication date pub_date = article.find(".//pub-date") if pub_date is not None: year = pub_date.find("year") month = pub_date.find("month") day = pub_date.find("day") date_parts = [] if year is not None: date_parts.append(year.text) if month is not None: date_parts.append(month.text) if day is not None: date_parts.append(day.text) article_data["publication_date"] = "-".join(date_parts) # Extract authors author_elems = article.findall(".//contrib[@contrib-type='author']") for author_elem in author_elems: surname = author_elem.find(".//surname") given_names = author_elem.find(".//given-names") author = {} if surname is not None: author["surname"] = surname.text if given_names is not None: author["given_names"] = given_names.text if author: article_data["authors"].append(author) # Extract full text (combining all paragraphs) body = article.find(".//body") if body is not None: paragraphs = body.findall(".//p") article_data["full_text"] = " ".join("".join(p.itertext()).strip() for p in paragraphs) f.write(json.dumps(article_data) + "\n") saved += 1 print(f"Saved batch {i//batch_size + 1}") print(f"Downloaded {saved} articles to {out_file}, {skipped} articles removed by license filter") Now you can call your function with your query to create your corpus. For example: # Install packages if neededpip install python-dotenv requestsquery = 'bacterial pneumonia treatment'max_results = 500batch_size = 50download_pmc_articles(query, max_results, batch_size) And that’s it! Now all your articles are saved in a jsonl file and ready to be processed for RAG What’s Next: Preparing the Data for RAG In Part 2, we’ll take the domain-specific corpus you just built and use it to power a Retrieval-Augmented Generation (RAG) system — grounding your LLM in real evidence to reduce hallucinations and improve trust. Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor. Published via Towards AI

The virtual pet Tamagotchi is kept alive by feeding it right and clearing its droppings, but the game has lost its luster. The egg-shaped tiny computer game that had the world in a frenzy once is rekindled from the ruins, in a bolder, bigger, and humanized format, by a YouTuber, and we are amazed at the detail and finesse Terence Grover has managed in his version of the Tamagotchi. Comprising 3D components and Raspberry Pi as the brain, Grover’s Tamagotchi is a representation of real life. The entire creation is based on the classic Tamagotchi game, but it is tied closely to Abraham Maslow’s pyramid of hierarchy of needs, building up from physiological needs to safety, love and belonging, to esteem and self-actualization at the top. The game is simple: keep the virtual pet alive, catering to all possible human needs. You miss one, and the Tamagotchi is no more! Designer: Terence Grover According to Grover, the idea of the real-life simulating Tamagotchi was born from the intention to “build a parody of life simulator games,” which would combine pixel art, game design, electronics, and humor. The result is this fun game, that gets serious as you take the Tamagotchi through all the life’s hardships – Job, Debt, etc, Grover says – to earn money that you need to feed and keep the little creature alive. So instead of the cute creature and the simple feeding game, you are here negotiating the “cynical arc of human life,” going through all the levels of Maslow’s pyramid to increase your pet’s life expectancy. The entire building and rebuilding process is detailed in an interestingly edited YouTube video, which is getting one prominent reaction: Why so few views? The video that has amassed a little above 2.5k views in five days (at the time of writing) is filled with comments such as, “I don’t understand why it’s not viral. He literally did everything right.” Another commenter writes, “Great video, the storytelling is spot on. The amount of work you put into this video is crazy.” Grover has gone a tad fast with his voice over, which hasn’t gone down too well with some viewers, suggesting he go a little slower, “You have all the right content, but you are talking so fast that I have no idea what is actually going on.” Back to the real-life simulating Tamagotchi. Based on a random set of events and scenarios, it has a Raspberry Pi computer connected to a physical RGB LED matrix. It is controlled by three tactile buttons, like on the classic game device. It features a series of unlockable minigames based on “education, job, housing, socializing, hobby, rest, food” that you must toggle to keep the animated pet alive, whose life may be influenced by the choices you make. Find the logic interesting, you can head over to Grover’s Github to download. The post Real-life simulating Tamagotchi is nostalgic, challenging, and really fun first appeared on Yanko Design.

As the manufacturing industry faces challenges — such as labor shortages, reshoring and inconsistent operational strategies — AI-powered robots present a significant opportunity to accelerate industrial automation. At Automate, the largest robotics and automation event in North America, robotics leaders KUKA, Standard Bots, Universal Robots (UR) and Vention are showcasing hardware and robots powered by the NVIDIA accelerated computing, Omniverse and Isaac platforms — helping manufacturers everywhere automate and optimize their production lines. Deepu Talla, vice president of robotics and edge AI at NVIDIA, delivered a keynote on physical AI and industrial autonomy. “The manufacturing industry is experiencing a fundamental shift, with industrial automation and AI-powered robots increasingly changing how warehouses and factories operate worldwide,” said Deepu Talla, vice president of robotics and edge AI at NVIDIA. “NVIDIA’s three-computer architecture — enabling robot training, simulation and accelerated runtime — is empowering the entire robotics ecosystem to accelerate this shift toward software-defined autonomous facilities.” Synthetic Data Generation Blueprint Speeds Up Robot Development Pipelines Embodied AI systems, which refers to the integration of AI into physical systems, must be trained with real-world data — traditionally a complex and resource-intensive process. Each robot typically needs its own custom dataset due to differences in hardware, sensors and environments. Synthetic data offers a powerful alternative. NVIDIA Isaac Lab 2.1 — the latest version of the open-source robot learning framework, announced at Automate — provides developers with tools to accelerate the robot training process using the NVIDIA Isaac GR00T Blueprint for synthetic motion generation. Built on NVIDIA Omniverse, a physical AI simulation platform, and NVIDIA Cosmos world foundation models, the blueprint provides a reference workflow for creating vast amounts of synthetic and robot manipulation data, making it easier and faster to train robots, like manipulators and humanoids, for a variety of tasks. NVIDIA showcases the synthetic manipulation motion generation blueprint. Robotics Leaders Harness NVIDIA Technologies for Industrial AI Image courtesy of UR. Robotics leaders are building next-generation robots, tapping into NVIDIA technologies to train, power and deploy physical AI in industrial settings. Universal Robots, a leader in collaborative robotics, introduced UR15, its fastest collaborative robot yet, featuring improved cycle times and advanced motion control. Using UR’s AI Accelerator — developed on the NVIDIA Isaac platform’s CUDA-accelerated libraries and AI models, and NVIDIA Jetson AGX Orin — manufacturers can build AI applications to embody intelligence into cobots. Vention, a manufacturing automation company, announced MachineMotion AI, an automation controller designed to unify motion, sensing, vision and AI. The system taps into the NVIDIA Jetson platform for embedded computing and NVIDIA Isaac’s CUDA-accelerated libraries and models, enabling compute-intensive AI tasks such as real-time vision processing, bin-picking and autonomous decision-making. This technology shows the value AI brings to the manufacturing floor for practical deployment of robotic solutions. Standard Bots, a robotics developer, unveiled its manipulator, a 30kg-payload, 2m-reach robot that can be used for heavy-duty tooling and moving large objects in the automotive, aerospace and logistics industries. With NVIDIA Isaac Sim, a reference application built on Omniverse, robots can be taught tasks through demonstrations, eliminating the need for traditional coding or programming to free up developers for higher-value tasks. Standard Bots also announced teleoperation capabilities via a tablet device, which can efficiently collect training data. KUKA, a leading supplier of intelligent automation solutions, unveiled its KR C5 Micro-2, a small robot controller integrated with an NVIDIA Jetson extension for AI-ready applications. It will provide future KUKA robots with better AI vision and AI-based control tasks powered by NVIDIA’s software stack. NVIDIA Brings Software to Deploy AI Agents in Factories and Warehouses In addition to robots, manufacturers everywhere are increasingly turning to AI agents capable of analyzing and acting upon ever-growing video data. The NVIDIA AI Blueprint for video search and summarization (VSS), part of the NVIDIA Metropolis platform, combines generative AI, large language models, vision language models and media management services to deploy visual AI agents that can optimize processes, such as visual inspection and assembly, and enhance worker safety in factories and warehouses. This helps eliminate manual monitoring and enables rapid processing and interpretation of vast amounts of video data, helping businesses drive industrial automation and make data-driven decisions. Developers can now use their own video data to try the AI Blueprint for VSS in the cloud with NVIDIA Launchable. Industry leaders are using the blueprint for VSS to enable advanced video analytics and computer vision capabilities across domains. At Automate, Siemens will be showcasing its Industrial Copilot for Operations, a generative AI-powered assistant that optimizes workflows and enhances collaboration between humans and AI. Using the tool, shop floor operators, maintenance engineers and service technicians can receive machine instructions and guidance quicker, using natural language. The copilot uses NVIDIA accelerated computing and NVIDIA NIM and NeMo Retriever microservices from the AI Blueprint for VSS to add multimodal capabilities. Connect Tech, an edge computing company, is analyzing drone footage with the blueprint for VSS running on NVIDIA Jetson edge devices to enable real-time Q&A and zero-shot detections for hazards like fires or flooding in remote areas. DeepHow, a generative AI-powered video training platform provider, is using the blueprint to create smart videos that capture key workflows and convert them into structured training content, improving shop floor operator efficiency. InOrbit.AI, a software platform for robot orchestration, will showcase its latest improvements in InOrbit Space Intelligence, which harnesses physical AI, computer vision and the VSS blueprint to analyze robot operations and optimize real-world workflows. And KoiReader Technologies, a provider of vision and generative AI-powered automation solutions, is using the blueprint to enable true real-time operational intelligence from events occurring in supply chain and manufacturing environments. Explore the following talks to connect with NVIDIA and its partners at Automate: Industrial Autonomy in the Era of Physical AI — a keynote delivered by Talla AI to Make Human Operators Better: Leveraging Generative AI for Enhanced Worker Training and Assistance — featuring Alvin Clarke, senior developer relations manager at NVIDIA, and Sivakumar Lakshmanan, CEO of DeepHow AI Everywhere: How Intelligent Systems Are Reshaping Industrial Automation — a panel discussion featuring Christi DeCuir, senior director of robotics strategic alliances at NVIDIA Unlocking Interoperable Digital Twins for Smart Factory Innovation — featuring Heiko Wenezel, head of Omniverse segment sales at NVIDIA Accelerate AI-powered Automation: Vention’s Journey With NVIDIA — featuring Yichao Pan, product manager of Isaac Manipulator at NVIDIA, Francois Giguère, chief technology officer at Vention, and Jimmy Li, research scientist at Vention The Automate Startup Challenge — an event sponsored by NVIDIA and Microsoft, spotlighting early-stage robotics and automation companies as they pitch their solutions to a panel of industry experts Learn more about NVIDIA’s latest work in robotics and industrial AI at Automate, running through May 15.