AI News Archive: June 17, 2026 — Part 14
Sourced from 500+ daily AI sources, scored by relevance.
- Uncovering Sex Differences in the Drosophila Ventral Nerve Cord Through Connectome Alignment
There are now multiple Drosophila connectomes available, comprising both its brain and spinal cord - comparing these connectomes requires first classifying neurons into cell types. Existing approaches for cell typing typically require extensive manual curation. Here we present a new method that automatically aligns connectomes via network topology alone. Using two complete male ventral nerve cord (VNC) connectomes as references, we assign cell types to ~13,000 neurons intrinsic to the female VNC, and automatically identify sex-specific and sexually dimorphic cell types. We not only provide a comprehensive census of cell types across male and female nerve cords, but we uncover connectivity differences that underlie differences in function. We focus on circuits underlying song production in males and oviposition behaviors in females, and investigate the counterparts of these circuits across sexes. Our automated methods and analyses provide insights into sex differences in circuits that connect the brain and body, and pave the way for comparative connectomics at scale.
- MedAgent: A Retrieval-Augmented Clinical Decision Support Agent with Verifiable Evidence Grounding for Evidence-Based Medicine
Evidence-based medicine demands clinical answers that are not only fluent and medically plausible, but also anchored in traceable evidence, tailored to patient-specific clinical questions, sensitive to the hierarchy of evidence, and respectful of clinical safety boundaries. While general-purpose large language models (LLMs) exhibit strong medical language generation ability, they tend to lean on parametric memory, underuse retrieved evidence, hallucinate citations, conflate evidence levels, and draw conclusions that are not fully supported by the underlying literature. Such limitations pose particular risks in clinical decision support, where answer reliability, evidence traceability, and reasoning consistency are paramount. To address these issues, we present MedAgent, an evidence-based medical agent trained through an end-to-end pipeline that integrates supervised fine-tuning (SFT) cold start, reward modeling, and Group Relative Policy Optimization (GRPO). The agent is designed to execute a structured workflow encompassing clinical question understanding, PICO extraction, evidence retrieval, evidence stratification, citation-grounded answer generation, and quality evaluation. Specifically, a Qwen2.5-14B-Instruct backbone is first cold-started on 200 human-verified agent trajectories, equipping it with tool invocation, PICO parsing, structured response generation, and citation faithfulness. Next, a Qwen2.5-7B reward model is trained on 2{,}099 pairwise preference samples to provide semantic-level quality signals for evidence-based responses. Finally, GRPO reinforcement learning is conducted in a retrieval-augmented agent environment, where every rollout involves real evidence retrieval and is scored jointly by rule-based rewards and reward-model signals. To avoid over-reliance on training rewards, we further construct an independent evidence-based medical evaluation benchmark, MedTrustBench, which contains 200 clinical questions spanning 10 specialties and four difficulty levels. Each question is annotated with standardized PICO elements and rubric-based scoring criteria. The benchmark includes 1{,}187 rubrics across seven dimensions: question relevance, evidence hierarchy, evidence quality and timeliness, evidence-answer consistency, completeness and depth, logical rigor, and medical terminology. Under an identical RAG pipeline, retrieval tool, retrieval configuration, and evaluation protocol, MedAgentv17 attains 78.6 points, outperforming GPT-4.1 (75.3) and approaching GPT-5.4 (80.3). These results show that a 14B domain-aligned model can surpass strong general-purpose baselines on specialized evidence-based medical reasoning, while delivering practical advantages in cost, privacy, controllability, and hospital-oriented private deployment. The model and associated datasets are publicly released at https://www.modelscope.cn/profile/InfoxmedModel
- Deep learning for interactive and automated inner retinal layer segmentation in OCT images of patients with retinitis pigmentosa using limited training data
Purpose: New therapeutic strategies such as optogenetics have created a need for accurate tracking of inner retina degeneration in Retinitis pigmentosa (RP) patients. We introduce two tailored deep learning models to segment the RNFL (retinal nerve fibre layer), GCIPL (ganglion cell inner plexiform layer), INL (inner nuclear layer), CFT (central foveal thickness) and RPE (retinal pigment epithelium) in RP: The first is based on a Segment Anything Model (SAM), the second on nnU-Net. To our knowledge, SAM has not yet been applied to retinal layers in OCT data. Methods: SD-OCT images of a retrospective cohort of 37 RP patients were included. Data for four training cycles were prepared semi-automatically in MATLAB, then assessed and corrected by three expert graders. 1,700 segmented B-Scans from two open datasets were used for pretraining. For post-processing, semantic retinal boundary detection was developed. The final models, OCT-SAM and nnU-Net, were trained on 228 annotated RP scans. Detected layer thicknesses were validated against manual segmentation at 90 random points in 30 OCT B-Scans. Finally, OCT-SAM was tested on three RP cases with retrospective, longitudinal OCT data. Results: nnU-Net achieved a precision, recall and F-1 score of 0.96 while OCT-SAM performance resulted in slightly lower values of 0.93, 0.8 and 0.85, respectively. OCT-SAM measurements had low bias and good agreement with manual annotations, confirming reliability. Conclusions: OCT-SAM enabled fast data annotation and tool integration, whereas nnU-Net provided the best segmentation performance. OCT-SAM demonstrated longitudinal reproducibility and detected RP-characteristic pathologies and degenerative changes. Future work will extend OCT-SAM to 3D OCT segmentation.
- What Urine Measures Is Not What Tissue Encodes: Compartment-Specific miRNA Coordination in Prostate Cancer
Abstract Background Prostate cancer (PCa) diagnosis remains challenged by the limited specificity of prostate-specific antigen (PSA) testing, which cannot reliably distinguish malignancy from benign prostatic hyperplasia (BPH). MicroRNAs (miRNAs) are emerging candidates for liquid biopsy-based diagnostics, but most studies assess expression in isolation within a single compartment (biological source - Tissue, blood, serum, urine etc.), overlooking both compartment-specific behavior and the coordinated relationships among miRNAs. Methods We profiled four candidate miRNAs --- miR-19b-3p, miR-21-5p, miR-101-3p and miR-375-3p, across four biological compartments (prostate tumor tissue, urine, serum, and blood) in 179 patients undergoing prostate biopsy for clinical suspicion of PCa (104 PCa, 75 BPH) using qRT-PCR. Urinary exosomal RNA was isolated with a commercial exosome isolation kit so from here onwards this compartment will be referred to as urine. Differential expression was quantified using Cohen's d; inter-miRNA coordination was assessed via Spearman correlation and differential correlation ({delta} r) analysis; and a compartment-level network rewiring score was derived as the sum of {delta} r| across miRNA pairs. Cross-compartment structural alignment was evaluated by comparing correlation patterns at the population level. Diagnostic models combining PSA, age, and urinary exosomal-miRNA features were evaluated using Logistic Regression, Elastic Net Logistic Regression and Naive Bayes classifiers under leave-one-out cross-validation (LOOCV). Results Effect sizes were largest and most consistent in urine, with miR-101-3p showing the strongest separation between PCa and BPH (d = -1.01), followed by miR-21-5p (d {approx}-0.72$) and miR-19b-3p (d {approx}-0.64). Two markers (miR-19b-3p, miR-375-3p) showed directional reversals across compartments, indicating that disease-associated signals are compartment-specific rather than uniformly conserved. In tumor tissue, PCa was associated with substantial reorganization of inter-miRNA coordination (network rewiring score = 2.46), including the emergence of a strong miR-21-5p--miR-375-3p co-regulatory axis ({delta} r = +0.87$) and decoupling of the miR-21-5p--miR-19b-3p relationship ({delta}r = -0.64$). Urine showed a structurally distinct coordination pattern (rewiring score = 1.77), dominated by a miR-101-3p--miR-19b-3p axis (r = +0.56) absent from tissue; cross-compartment comparison showed concordance in only 1 of 5 miRNA pairs, indicating that urine's architecture is largely independent of tissue's. For diagnostic translation, the conventional PSA cutoff (4 ng/mL) achieved 100% sensitivity but only 23.5% specificity. In urine, miR-101-3p performs better than other miRNAs, with AUC of 0.77 (95% CI: 0.62--0.90). Adding PSA and age to the urinary miR-101-3p further improved discrimination to an AUC of 0.91 (95% CI: 0.82--0.99), with 70% specificity at 92% sensitivity; this pattern was consistent across Elastic Net and Logistic Regression classifiers. Expanding the model to include all urinary miRNAs, age, and pair-derived coordination features did not improve on this result (AUC = 0.88), indicating that population-level coordination changes did not translate into additional individual-level diagnostic value in this cohort. Conclusions miRNA signals in extracellular compartments do not represent direct surrogates of tumor-level molecular architecture; each compartment harbors a distinct, transformed coordination structure reflecting its biological context. While these coordination-level changes are mechanistically informative, the most direct translational gain in this study came from a parsimonious model combining PSA, age with a single urinary marker, miR-101-3p, which improved AUC from 0.77 to 0.91, with specificity 70.5% at 90% sensitivity criteria. This combination represents a promising, interpretable candidate for reducing unnecessary prostate biopsies, pending validation in larger, independent cohorts. Keywords: MicroRNA, Compartment-Specific Biomarkers, Urinary Exosomes, Differential Correlation, Liquid Biopsy, Machine learning, PSA, Early diagnosis
- Cross-Device Adaptation of Mirai for Mammography-Based Breast Cancer Risk Prediction
Fine-tuning can adapt pretrained medical imaging models to new clinical datasets, but device-specific domain shifts may limit generalizability. We evaluated Mirai, a mammography-based deep learning model for breast cancer risk prediction, in a large screening cohort containing Hologic and General Electric (GE) full-field digital mammography systems, including GE Premium View (GE PV) and Tissue Equalization (GE TE) post-processing software. Native Mirai showed lower performance on TE images than on Hologic or PV images. Fine-tuning on TE images improved TE performance, particularly for short-term risk prediction, but substantially reduced performance on Hologic images, consistent with catastrophic forgetting. To mitigate this effect, we developed a device-invariant model using interleaved multi-device sampling and conditional adversarial training. This approach largely restored Hologic performance while maintaining improved TE performance, providing better robustness across heterogeneous imaging platforms. Comparison of cumulative and annual risk AUCs over a five-year time horizon further showed that performance gains were driven mainly by short- and intermediate-term predictions. These findings highlight both the value and dangers of device-specific fine-tuning and support balanced domain-adaptation strategies for deploying mammography-based risk models across diverse clinical imaging environments.
- LLM-Driven Extraction of NI-RADS and Imaging Tumor Characteristics to Enhance Oropharyngeal Cancer Survivorship Surveillance
Abstract Purpose Radiologic surveillance is essential for oropharyngeal cancer (OPC) survivors, guiding recurrence detection and follow-up strategies. The Neck Imaging Reporting and Data System provides a standardized framework for post-treatment risk reporting at both the primary tumor site (pNI-RADs) and cervical lymph nodes (nNI-RADS). Comprehensive surveillance additionally requires assessment of disease status, including the primary tumor, nodal involvement, and distant metastases. These clinical results are often embedded as unstructured data within free-text radiology reports. We hypothesized that a large language model (LLM) can reliably extract NI-RADS score criteria and summarize key imaging features from unstructured radiology text, achieving high concordance with expert review. Methods Previously untreated OPC patients who received definitive cancer therapy were identified. Eligible imaging reports included post-treatment head and neck CT, MRI, or FDG PET/CT scans containing narrative and impression text. Examinations lacking narrative or impression text, containing pre-existing NI-RADS annotations, or involving non-surveillance imaging modalities were excluded. A total of 200 reports were randomly selected from 7,076 eligible examinations for manual abstraction using a three-reviewer consensus framework to establish a reference dataset. Using the Palantir Foundry Pipeline Builder, a GPT-5-based LLM was deployed to extract pNI-RADS and nNI-RADS scores, and key imaging features of disease status from these reports. Performance was evaluated using exact agreement and F1-based metrics. Results Agreement for no evidence of disease (score of 1) was 93.3% (126/135; F1 = 0.94) and 90.3% (130/144; F1 = 0.93) for pNI-RADS and nNI-RADS, respectively. For NI-RADS [≥]2, exact category agreement was 73.1% (38/52; macro-F1 = 0.75) for pNI-RADS and 64.3% (27/42; macro-F1 = 0.56) for nNI-RADS. Quadratic weighted {kappa} was 0.81 and 0.59, respectively. For post-treatment disease surveillance variables, agreement was 94.9% (149/157; F1 = 0.87) for primary tumor presence, 89.1% (164/184; F1 = 0.87) for nodal disease presence, and 94.7% (126/133; F1 = 0.70) for distant metastasis detection. Specificity was high across disease-status variables (0.95-0.99), with negative predictive values of 0.95 for primary tumor, 0.87 for nodal disease, and 0.99 for distant metastasis. Conclusions Our LLM-based information retrieval and classification approach for radiographic treatment response from unstructured, multidimensional imaging reports achieved high performance for disease exclusion and moderate performance for detecting suspected residual and/or new disease. This pipeline supports scalable and standardized surveillance data capture for longitudinal monitoring, clinical analytics, and survivorship research in head and neck oncology.
- Identifying anaphylaxis using weakly-supervised prediction models and natural language processing
Objectives Scalable computable phenotyping algorithms are critical for conducting high-throughput disease-outcome research in large, distributed-data electronic health record (EHR) and claims data settings. We developed and evaluated a claims- and EHR-based computable phenotyping algorithm for anaphylaxis, a rare acute condition that is challenging to accurately identify using claims data alone. Materials and Methods Potential anaphylaxis events came from two healthcare systems (Kaiser Permanente Washington [KPWA] and Vanderbilt University Medical Center [VUMC]). We engineered features from clinical text using automated natural language processing (NLP) methods. We then developed a phenotyping algorithm using four NLP- and diagnosis code-based silver labels (proxies for the gold-standard labels). Gold-standard abstracted outcomes were used to evaluate algorithm performance. Results The largest area under the receiver operating characteristic curve (AUC) was 0.931 for an NLP-based silver-label model at KPWA. Depending on the model and healthcare system site, positive predictive value (PPV) and sensitivity at the threshold of predicted probability that maximized F1 score ranged from 0.52 to 0.77 (PPV) and 0.78 to 1 (sensitivity). Discussion NLP-based silver-label models had large AUC at KPWA but not at VUMC. This may be because clinical text at KPWA is only available for outpatient encounters and secure messaging. High sensitivity for identifying anaphylaxis can be obtained using our best-performing models. Conclusion The best-performing models had better PPV and sensitivity tradeoffs than prior bespoke anaphylaxis models with costly, manually curated features. The simplicity of the approach compared to traditional phenotyping methods allows it to be deployed easily at multiple health care systems.
- Wearable-Grade Lead Reduction Disproportionately Degrades ECG AI Performance in Elderly Patients: Evidence from PTB-XL and MIT-BIH
Consumer wearable devices increasingly use single-lead electrocardiograms (ECGs) for cardiac monitoring, but these signals contain substantially less spatial information than the clinical 12-lead standard. Whether this reduction dispro- portionately affects older adults, who often present with more complex cardiac conditions, remains poorly understood. In this study, we evaluated the impact of lead reduction on AI-ECG diagnostic performance across age groups. A 1D resid- ual neural network was trained on 21,091 PTB-XL ECG recordings spanning five diagnostic superclasses and assessed using 12-, 6-, 2-, and 1-lead configurations. Under the full 12-lead setting, model accuracy declined from 84.5% in patients younger than 40 years to 66.2% in patients aged 75 years or older. Progressive lead reduction further widened this gap. Under the 1-lead configuration, accuracy decreased by 14.1 percentage points in the 75+ group but by only 0.4 percent- age points in the <40 group, representing an approximately 40-fold differential degradation confirmed by three independent statistical tests (all p < 0.0001). Older adults also exhibited greater multi-condition diagnostic complexity, pro- viding a plausible explanation for their increased vulnerability to information loss. External validation on the MIT-BIH Arrhythmia Database confirmed cross- dataset model stability. These findings suggest that age-stratified performance reporting should be a minimum standard in wearable AI-ECG validation and regulatory assessment.
- remio: Your Personal ChatGPT
Get Tailored Answer with Your Personal ChatGPT
- SpaceX buys AI coding startup Cursor for $60 billion in race for an edge over Anthropic and OpenAI
SpaceX buys AI coding startup Cursor for $60 billion in race for an edge over Anthropic and OpenAI Austin American-Statesman
- LLM Observatory
Real-time observability for Claude & OpenAI APIs
- Docfarm
Host, share, and track everything your AI builds
- NEXIA
The AI assistant that thinks like a senior engineer
- Kommanda
A dual-pane file manager with AI for macOS
- It’s ‘unavoidable’: Apple says it will be forced to raise prices due to the AI boom
Tech giants are gobbling up memory chips for AI servers, leaving Apple with soaring component costs that Tim Cook says will inevitably be passed on to consumers.
- Apple says it will be forced to raise prices due to the AI boom
Apple says it will be forced to raise prices due to the AI boom
- As AI Power Demands Soar, Anthropic Makes an Unprecedented Sustainability Move
The developer of Claude recently announced that it had joined a coalition of companies dedicated to buying carbon removal.
- World model maker Odyssey nabs $1.45B valuation backed by Amazon and other big names
World models are the next big thing in AI beyond LLMs and, with this round, Odyssey has cemented itself as one of the startups to watch.
- AI lab Odyssey valued at $1.45 billion in latest funding round
AI lab Odyssey has secured $310 million in a funding round. This investment values the company at $1.45 billion. Natural Capital led the Series B round. Amazon, AMD Ventures, GV, EQT, and IQT also participated. Odyssey is developing AI systems that learn to predict and interact with the world. The field is advancing rapidly.
- Only 16 percent of Americans think AI will have a positive impact on society, a new study shows
Although Wall Street loves AI, every day Americans are significantly less optimistic about the industry, a new report from Pew Research shows.
- Google bets on Gemini to reinvent the smart home speaker
Google is betting generative AI can breathe new life into the smart speaker. The company's new $99.99 Google Home Speaker replaces the rigid commands of the Google Assistant era with more conversational Gemini interactions.
- The Gemini-Powered Google Home Speaker Is Finally Here
Arriving six years after Google’s last smart speaker, the new HomePod-style device was redesigned to play host to Gemini’s chatbot.
- The new Google Home Speaker can run your house with Gemini for $99
The new Google Home Speaker was made with Gemini in mind, and can take natural-language commands.
- Preorders Open for Next-Gen Google Home Speaker With Gemini Smarts
Preorders Open for Next-Gen Google Home Speaker With Gemini Smarts PCMag Australia
- Preorders Open for Next-Gen Google Home Speaker With Gemini Smarts
Preorders Open for Next-Gen Google Home Speaker With Gemini Smarts PCMag
- Google’s new $99 Home Speaker offers 360-degree audio and next-gen Gemini perks
Gemini replaces Google Assistant; you get 360-degree audio and four color options, and the Nest Audio is officially discontinued.
- Google’s new Gemini-powered smart speaker is finally available for pre-order
It comes with six months of Google Home Premium.
- Google’s Gemini-powered AI home speaker goes on sale June 25
Google’s Gemini-powered AI home speaker goes on sale June 25 The Mercury News
- Google’s Gemini-powered AI home speaker goes on sale June 25
Google’s Gemini-powered AI home speaker goes on sale June 25 East Bay Times
- AI startup Pramaana Labs raises $27 million in seed funding led by Khosla Ventures
Pramaana Labs, an AI startup, has secured $27 million in seed funding. The company develops technology to ensure AI answers are mathematically verifiable. The startup will use the new funding to train Pramaana's formalisation and proof-checking models, expand its AI research staff, and venture into regulated areas such as tax, medical diagnosis, cybersecurity and financial compliance.
- Pramaana Labs Raises $27 Mn To Build AI Verification Layer
AI startup Pramaana Labs, a startup that is building a “verification layer” for AI, has raised $27 Mn (about ₹258…
- Pramaana Labs raises $27M to make AI prove its answers
Formal verification startup Pramaana Labs Inc. today said it has raised $27 million in seed funding for a system it describes as a compiler for high-stakes artificial intelligence. The product checks an AI model’s answer against the rules of a domain and will not return it unless it can be proved correct. Pramaana is going after […] The post Pramaana Labs raises $27M to make AI prove its answers appeared first on SiliconANGLE .
- AI Health Startup Wants to Assist Half of Latin American Doctors
An Andreessen Horowitz-backed healthcare startup born in Latin America wants to put its AI assistant in the hands of half the region’s 1.9 million doctors by the end of 2027, a bet that technology can help bridge a shortage of medical professionals across strained health systems.
- Meta head of product for 'AI for work' transformation is leaving company
Meta is hitting a new chapter as Emily Dalton Smith, a key executive with a longstanding history at the company since 2015, exits. Her leadership in revamping internal AI tools was instrumental during a time of massive restructuring, which coincides with Meta's shift in AI strategy.
- At G7, Macron says he expects progress on broadening access to Anthropic's Mythos
At G7, Macron says he expects progress on broadening access to Anthropic's Mythos The Straits Times
- Trump says negotiations with Anthropic are 'going fine'
Trump says negotiations with Anthropic are 'going fine' Reuters
- Trump Says Anthropic Negotiations Continue as AI Leaders Huddle at G-7
The president made his comments at a Group of Seven summit where some world leaders were concerned about losing access to leading AI tools.
- Trump says negotiations with Anthropic are 'going fine'
US President Donald Trump stated that talks with artificial intelligence firm Anthropic are progressing well. This follows a meeting with Anthropic CEO Dario Amodei at the G7 summit. The administration has raised national security concerns regarding foreign access to Anthropic's advanced AI models. The company had previously blocked access to these models after a presidential order.
- Trump says negotiations with Anthropic are 'going fine'
Trump says negotiations with Anthropic are 'going fine' The Straits Times
- 'A signal of where power sits': Trump and world leaders joined by OpenAI, Anthropic, Google at G7
Frontier AI risks, infrastructure and sovereignty are all expected to be discussed at the world leaders' summit.
- From RAG to ontology: Databricks bets on context as the key to trusted AI agents
First came vector databases, then RAG. Now, the next frontier in enterprise AI is taking shape: context layers that give autonomous agents a shared understanding of the business, a vision Databricks is advancing with Genie Ontology. Currently in preview, Genie Ontology automatically extracts business context from enterprise data, dashboards, queries, pipelines, documents, and applications and organizes it into a living graph that AI agents can use to understand how an organization operates. Showcased at the company’s Data + AI Summit, Genie Ontology uses a ranking system inspired by Google’s PageRank to identify the most authoritative business definitions within an organization. Rather than treating all sources equally, it weighs factors including who created the information, how widely it is used, its links to certified datasets and assets, and how recently it was updated before determining which answer an AI agent should rely on, Databricks CEO Ali Ghodsi said during his keynote late on Tuesday while explaining the new offering. Organizations can also upload their own business definitions or ontologies to Genie Ontology via Databricks’ existing Unity Catalog Semantics platform, Ghodsi added. Ontology promises consistency, but readiness remains a hurdle For CIOs, a unified context layer, such as Genie Ontology, will materially improve consistency, trust, and governance for enterprise AI deployments, according to analysts. “One definition feeding every agent means you stop getting three different answers to the same question,” said Michael Leone , principal analyst at Moor Insights and Strategy. “Older approaches, such as RAG and vector search, just pull back whatever looks similar to your question, and they don’t actually understand your business. An ontology gives the agent the meaning a catalog can’t, what your terms mean, and which source to trust,” Leone added. That improvement in consistency, according to Ashish Chaturvedi , leader of executive research at HFS Research, could also improve trust, which remains one of the most critical barriers to AI adoption. “The single biggest barrier to enterprise AI adoption is that decision-makers don’t trust AI outputs enough to act on them without checking. An ontology that grounds answers in governed business definitions, with lineage back to source, directly attacks that trust deficit,” Chaturvedi said. Alternatively, Leone was more cautious about the trust argument: “It’s a promising idea, but it still has to prove itself before I’d lean on it for anything that matters.” Echoing Leone, HyperFRAME Research’s practice leader of AI stack Stephanie Walter pointed out that ontologies have a missing link, and that is verification: “Ontologies can improve context, but they do not guarantee the answer is correct. An agent can still pull incomplete data, apply the wrong logic, skip rows, misunderstand a workflow, or take the wrong action.” That verification gap becomes even more critical, according to Leone, because most enterprises don’t have the data and governance readiness required to implement an ontology layer for AI deployments: “If your data and governance aren’t already in order, this just speeds up your existing mess.” Seconding Leone, Walter pointed out that an ontology cannot fix messy definitions, poor lineage, weak ownership, or fragmented permissions on its own. Additionally, the analyst pointed out that the hard part for CIOs is not creating an ontology once but keeping it accurate as the business changes: “Enterprises will need clear data ownership, metric ownership, domain expertise, governance processes, and a way to resolve conflicting definitions.” “Otherwise, the ontology becomes another stale metadata project with a more sophisticated name,” Walter added. A growing risk of CIO confusion Beyond data and governance readiness, CIOs also face a growing risk of confusion in the wake of several technology vendors pursuing approaches, similar to Genie Ontology, to ground enterprise AI in a business context, according to analysts. Over the past year, Snowflake, Microsoft, and others have introduced some form of ontology, semantic, and context-layer offerings, but the problem is in how these offerings are named, Leone said. “Everyone slapped a different name on basically the same idea. It slows people down as it creates confusion,” Leone noted. That confusion could also backfire on Databricks and other vendors, according to Bhupendra Chopra , cofounder and CRO of IT consulting firm Kanerika: “While the marketing has converged around context-building offerings, most enterprises will choose the platform where their data already resides.” HFS Research’s Chaturvedi doubled down on that view, saying CIOs should resist evaluating ontology offerings in isolation and asked them to stick to the mantra of context layer follows data gravity: “If your data lives in Databricks, Genie Ontology is your path. If it’s in Snowflake, Horizon Context is. If you’re a Microsoft shop, the IQ family is.” Additionally, Chaturvedi urged CIOs to look beyond functionality and assess how open and portable these offerings are, particularly in multi-platform environments where business definitions may need to move across data lakehouses , analytics tools, and AI platforms. This is where Chaturvedi sees Snowflake differentiating itself from rivals, with its focus on open semantic interoperability aimed at reducing the risk of semantic lock-in as enterprises evolve their data and analytics stacks. The battle for the AI control plane Snowflake’s efforts to differentiate itself, though, analysts pointed out, at least for CIOs, draw attention to a larger race among vendors, including Databricks, to become the control plane for enterprise AI. While Snowflake is attempting to position itself as an AI control layer through a combination of Snowflake Intelligence , Horizon Catalog, and its push for open semantic interoperability, Microsoft is embedding business context and governance across its Copilot, Fabric, and broader AI stack through offerings such as Work IQ, Fabric IQ, and Foundry IQ, Chaturvedi said. Databricks’ Genie Ontology, too, is part of a similar strategy, Chaturvedi pointed out, urging CIOs to view the offering in the context of the company’s wider effort to position its lakehouse platform as the foundation on which enterprise AI agents are built, governed, and eventually deployed. “It’s absolutely a control-plane play. When you connect the dots across everything Databricks has announced at this summit, including LTAP , OpenSharing , and Genie Ontology, you see a single place where enterprise data, governance, business semantics, and agent execution all converge,” Chaturvedi added. Further, the analyst noted that the control-plane strategy reflects Ghodsi’s broader vision that data platforms could evolve into what the CEO describes as an “agentic system of record” — an authoritative source that AI agents read from, reason over, and act through. The concept mirrors earlier platform shifts, Chaturvedi said, where ERP systems became the system of record for business transactions and data warehouses became the system of record for analytics. The next battle, the analyst said, is over which platform becomes the system of record for enterprise AI agents. Moor Insights and Strategy’s Leone agreed that data platforms are well-positioned to compete for that role because they already own the data, governance controls, lineage, and permissions that agents require to operate safely at scale. Still, analysts cautioned that context alone will not determine which vendor comes out on top. “The next enterprise AI battleground is not just context. It is verifiable execution,” Walter said. The article originally appeared on InfoWorld .
- Sarvam AI's Pratyush Kumar joins AI executive huddle with G7 leaders
Pratyush Kumar of Sarvam AI joined top global AI leaders for a G-7 working lunch. The meeting focused on AI and the Digital Age. Leaders from the US, France, and other G-7 nations were present. This event highlights Sarvam AI's growing international recognition. The company recently achieved unicorn status.
- At G7, euro AI sovereignty push intensifies after US blocks Anthropic models
At G7, euro AI sovereignty push intensifies after US blocks Anthropic models Computing UK
- AI executives gather at G7 as Europeans seek checks on American dominance
Artificial intelligence takes center stage Wednesday at the G7 meeting in France
- As G7 wraps, OpenAI and Anthropic meet with world leaders to discuss the future of AI
The Group of Seven wraps up three days of talks in the French Alps on Wednesday with discussions on the contentious future of artificial intelligence and U.S. dominance of the industry . Executives of leading AI companies including OpenAI CEO Sam Altman , Google DeepMind CEO Demis Hassabis and Anthropic CEO Dario Amodei are attending discussions as U.S. President Donald Trump and other leaders close formal talks of the leading industrial nations in the lakeside resort of Evian-les-Bains with a session on the future of artificial intelligence and another on fostering economic growth. Trump plans to stop outside Paris for a glitzy dinner at the Palace of Versailles before jetting back to Washington on Wednesday. The G7 leaders spent the bulk of the meetings Tuesday discussing the war between Russia and Ukraine and a tentative deal to end the Iran war . Trump did not reveal details of the agreement expected to be signed by the United States and Iran on Friday in Switzerland, saying “nobody knows what it is but it’s very strong.” The G7 includes France, Canada, Germany, Italy, Japan, the U.S. and the United Kingdom. Guest nations at this summit include Brazil, Egypt, India, Kenya, South Korea, Qatar, Ukraine and the United Arab Emirates.
- Big Tech’s AI Datacenter Investments Might Be In Big Trouble
Chinese open models like GLM-5.2 and DeepSeek-V4 now rival frontier AI at a fraction of the cost, and that could strand the data center bet hyperscalers made.
- The AI boom that would make AI data centers in space necessary may not last
AI infrastructure spending has never been larger. Efficiency gains are eroding the demand assumptions that make orbital data centers worth building
- AI data centers — in space
As resistance to massive data centers grows on Earth, companies like SpaceX and Google are exploring AI infrastructure in orbit instead
- Clearlake-backed Quest Software Acquires Anetac to Advance Identity Security for the Agentic AI Era
Clearlake-backed Quest Software Acquires Anetac to Advance Identity Security for the Agentic AI Era Toronto Star
- Jeff Bezos says cost is the only barrier to data centers in space — and that AI will create jobs
The Amazon founder also pushed back on fears that AI will eliminate jobs, predicting a labor shortage instead