AI News Archive: June 26, 2026 — Part 6
Sourced from 500+ daily AI sources, scored by relevance.
- AI Made Building Startups Too Easy: Winning Customers Is The Real Challenge
The bottleneck to creating a startup is no longer building the software, but getting people to care.
- [CVPR 2026] An upcycling method for creating true experts within a Mixture-of-Experts structure
[CVPR 2026] An upcycling method for creating true experts within a Mixture-of-Experts structure
- AI Is Changing Cyber Risk. Here’s How SMBs Can Respond.
Amid a surge in cyberattacks, security expert Daniel Dobrygowski shares steps every small to midsize business can take to avoid being an easy target.
Score: 45🌐 MovesJun 26, 2026https://hbr.org/2026/06/ai-is-changing-cyber-risk-heres-how-smbs-can-respond - FORHU’s SCL Architecture Sets New Standard for AI Governance at VivaTech 2026
FORHU’s SCL Architecture Sets New Standard for AI Governance at VivaTech 2026 azcentral.com and The Arizona Republic
- Drone vs. shoplifter: Watch how Redmond PD tracks an alleged thief from high in the sky
A shoplifting call this week at a Target store in Redmond, Wash., prompted a response as part of that city's Drone as First Responder program. Read More
- iPhone 18 could get a RAM boost, but only a tiny sliver to run AI chores in iOS 27
A new report claims the iPhone 18 could get 9GB of RAM to better support Apple Intelligence in iOS 27, while Pro models may remain at 12GB.
- What SUNY’s Systemwide AI Policy Means for Public University IT Leaders
Leaders at the State University of New York’s 64 campuses have until the end of the year to establish or update artificial intelligence guidelines, including standards for bias evaluation, student data privacy and responsible AI use. The mandate comes from a binding AI governance policy passed in May, leaving higher ed IT leaders at SUNY campuses to devise ways to evaluate AI vendors, implement governance workflows, protect institutional data and support responsible AI adoption at scale. The framework is already having an impact beyond the Empire State, with CIOs and IT leaders across…
Score: 45🌐 MovesJun 26, 2026https://edtechmagazine.com/higher/article/2026/06/suny-ai-policy-higher-ed-it-governance-perfcon - Jira Filters: What We've Shipped, What's Next & the Future of AI Filtering
Jira Filters: What We've Shipped, What's Next & the Future of AI Filtering Atlassian Community
- Dream it, plan it, launch it with AI-powered project templates
Dream it, plan it, launch it with AI-powered project templates Atlassian
- Pacdora Launches Canvas: An AI Workspace for Multi-SKU Packaging Design
Pacdora Launches Canvas: An AI Workspace for Multi-SKU Packaging Design USA Today
- Inside the UAE university building AI beyond chatbots, creating 'genesis of new ideas'
Inside the UAE university building AI beyond chatbots, creating 'genesis of new ideas'
Score: 42🌐 MovesJun 26, 2026https://www.khaleejtimes.com/uae/inside-uae-university-building-ai-beyond-chatbots-mbzuai-eric-xing - Autonomous security agents need complete data. Here's how to check if yours is ready.
An endpoint agent cannot report its own absence. The 2026 Axonius Actionability Report , conducted with the Ponemon Institute and surveying 662 IT and security professionals, put a number on a gap SOC teams have worked around for years. Across the Axonius customer base , 12.7% of devices in a 298,000-device median inventory are missing their expected security agent. If a device has no agent, no management console shows it. If a CMDB record is stale, no reconciliation flags it. An employee who installed Claude Enterprise outside procurement created a SaaS workspace, identity surface, and API-token footprint that endpoint telemetry alone will not reliably inventory. The coverage percentage on the EDR dashboard is structurally incomplete because the reporting mechanism cannot see what it does not cover. That gap matters more now than it did six months ago. SOC and XDR vendors are pushing more autonomous investigation and remediation into production. Those agents will query the same dashboards, trust the same coverage percentages, and act on the same blind spots human analysts learned to work around. A human analyst second-guesses a 98% coverage number. An autonomous agent treats it as ground truth and moves at machine speed. Three independent signals converged on the same gap Gravitee’s 2026 survey of 900-plus executives found 88% reported confirmed or suspected AI-related incidents, and only 14.4% sent agents live with full security approval. The Axonius/Ponemon report found 52% of respondents would let autonomous agents act on recommendations — while 63% said the underlying data lacks important information. The CSA's Agentic Trust Framework requires verified data governance before agents act on any finding. Mike Riemer, Field CISO at Ivanti , said that known vulnerabilities on Azure’s honeypot networks are now attacked in under 90 seconds. “Traditional security measures continue to work,” Riemer told VentureBeat. The caveat is that those measures only protect what they can see. An EDR agent deployed across 87.3% of the device inventory leaves the remaining 12.7% outside that agent’s telemetry, policy enforcement, and detection logic. Exclusive deployment data quantifies the scale Joe Diamond, CEO of Axonius, told VentureBeat that the average CISO sees roughly 50% of what is actually on the network. “Say 50% of their environment is sitting in dark matter,” Diamond said. “They don’t know what it is, or where it is, or who has access to it, if it’s secure, if it’s not secure.” Deployment data from more than 900 Axonius customers confirms those numbers. TransUnion went from 70% to 99% endpoint coverage after out-of-band verification. Western Union went from 85% to 99% by consolidating data from 38 tools and cutting manual workload by half. Lumen discovered 1.1 million assets, where the CMDB showed 17,000. That translates to roughly 37,000 unmanaged endpoints per organization sitting outside every policy, every patch cycle, and every detection rule. Diamond pointed to Mythos , Anthropic’s frontier reasoning model, as a sign that machine-speed offensive capability will make any unknown asset far riskier than it is today. “People tend to have shiny object syndrome,” he said. “If you didn’t understand what 50% of your environment looked like from a traditional endpoint perspective, and you think you’re going to wind sprint to granular control and governance of AI, your program will fail.” Diamond called the broader AI shift “as big, if not bigger than the internet.” Three approaches compete to close the gap No single architecture solves the visibility problem today. Three approaches compete, each with named tradeoffs security teams should evaluate before procurement. A dedicated integration layer uses bidirectional API adapters to build an always-current inventory. Axonius runs 1,400-plus adapters and now discovers shadow Claude Enterprise installations via its Anthropic adapter (GA June 15). “We created a bidirectional API integration with all the IT systems and all the security controls to build an always up-to-date inventory of what the environment looks like,” Diamond told VentureBeat. Platform-native EDR and XDR intelligence builds richer asset context inside the agent footprint. Depth within the agent footprint is the advantage. The limitation is structural. Platform-native intelligence is bounded by what the agent can see, and the gap the Ponemon report identified lives precisely where that visibility ends. CMDB modernization requires continuous reconciliation against three or more independent telemetry sources. Only 13% of organizations reconcile daily, according to Axonius/Ponemon data . The remaining 87% operate on stale records that feed incorrect prioritization into any automated remediation pipeline. EDR data readiness: Five gates before autonomous remediation Before you let autonomous SOC agents close tickets or quarantine assets, this checklist tells you whether your EDR and asset data is solid enough to trust. It is vendor-agnostic, works with any EDR and CMDB, and gives you five pass/fail gates you can run in a single working session. Risk Area What the data shows Readiness threshold Action to take now Asset inventory delta Ponemon: only 45% consolidate into a single view. Forrester TEI: 150% more assets than previously identified. Lumen: 17K in CMDB vs. 1.1M discovered. Delta ≤10% between discovery, CMDB, and EDR agent count. Delta above 10% blocks automated remediation until reconciled. Run API-based discovery against all segments. Diff against CMDB and EDR console count. Reconcile quarterly minimum. Unmanaged AI services Gravitee: 88% confirmed or suspected AI incidents. Only 14.4% with full security approval. Anthropic adapter (GA June 15) discovers unmanaged Claude Enterprise installations. No high-risk AI services outside approved procurement. Weekly SaaS discovery scans. Unmanaged high-risk instances trigger IR triage before exception review. Deploy SaaS discovery or protocol-level adapters for AI service detection. Automate weekly scans. Route unmanaged instances to IR queue. CMDB record accuracy Ponemon: only 13% reconcile daily (RSAC 2026). Brooks Running: 20% server discrepancy between console and independent discovery. Top remediation barriers: unclear prioritization, unclear ownership, inconsistent data. ≥85% of records validated against 3+ independent telemetry sources. No stale or orphaned records in active remediation queue. Cross-reference CMDB against cloud inventory, EDR telemetry, and IdP directory. Continuous reconciliation replaces annual audit cycles. Endpoint agent coverage gap Ponemon: an agent cannot report its own absence (p. 8). TransUnion: 70% to 99% after out-of-band verification. RSAC 2026: 12.7% of 298K median devices missing expected agent. ≥95% agent coverage verified via out-of-band discovery. Many CISOs set this as the minimum before allowing autonomous remediation. No self-reported-only metrics in board reports. Run network-based or API-driven discovery against managed device list. Coverage below 95% blocks automated remediation scoping. Asset ownership mapping Ponemon: 32% apply tags consistently. Only 51% assign ownership on new exposures (pp. 9, 16). TransUnion: 12K to 190K assets with ownership mapped. Owner assigned within 24 hours. Tags consistent across cloud, EDR, CMDB. Three systems showing three owners = failure. Automate ownership via cloud tags, IdP group membership, or CMDB metadata. Map asset, remediation, and business owner as separate fields. Five questions to ask before allowing autonomous SOC action What independently verifies endpoint-agent coverage outside the EDR console? How does the SOC reconcile conflicts between EDR, CMDB, cloud inventory, IdP, and discovery tools? Can AI agents act on assets with unknown or disputed ownership? Can the system distinguish “not vulnerable” from “not visible”? What data-quality gate blocks autonomous remediation when coverage or ownership falls below threshold? Board-ready risk framing Kayne McGladrey, IEEE Senior Member, has confirmed the pattern across multiple published VentureBeat interviews. The structural gap in self-reported coverage is not new. What is new is that autonomous agents will act on it at machine speed without the institutional workarounds human analysts developed over years of experience. Diamond put the board-level stakes plainly in an April 2026 press statement : “Findings pile up because the data isn’t trusted, ownership isn’t clear, and entire asset classes aren’t even in the picture.” The CSA’s Agentic Trust Framework requires that any agent promoted to a higher autonomy level must pass five gates, including demonstrated accuracy and a security audit. The EU AI Act’s Article 50 transparency obligations take effect August 2, 2026. The May 2026 Digital Omnibus pushed high-risk system obligations to December 2027, but organizations deploying agentic SOC agents on incomplete asset data face immediate operational risk that outpaces any regulatory timeline. The board-ready sentence: Our EDR coverage reports are structurally incomplete because an endpoint agent cannot report its own absence, and we are verifying coverage through out-of-band discovery before deploying autonomous agents that would act on those reports at machine speed. Security director playbook Run out-of-band asset discovery this week. Compare results against your CMDB export and EDR console count. If the delta exceeds 10%, halt automated remediation scoping until the gap is reconciled. Deploy SaaS discovery for AI services. Employees install AI ahead of procurement, ahead of security. Weekly scans are the minimum. Route any unmanaged high-risk instance to your incident response queue for triage before exception review. Map asset ownership to remediation responsibility. Ponemon found only 32% of organizations apply tags consistently. If three systems show three different owners for the same asset, automated remediation has no routing target. Fix the ownership layer before deploying agents that depend on it. Kill self-reported-only coverage metrics. Any risk calculation or board report that relies on EDR console-reported coverage alone is built on data the reporting system cannot verify. Require out-of-band verification for every coverage number that informs a risk decision.
- Teaching a Spreadsheet Engine to Teach Itself
Teaching a Spreadsheet Engine to Teach Itself
Score: 42🌐 MovesJun 26, 2026https://www.angellist.com/blog/teaching-a-spreadsheet-engine-to-teach-itself - ZTE CDO Cui Li at GTI Summit 2026: Co-creating an intelligent, ubiquitous 6G future and exploring new opportunities in the mobile AI era
PARTNER CONTENT: ZTE’s Chief Development Officer outlines the company's "2+4" framework for 6G convergence and industry-wide collaboration in the mobile AI era
- Forget the score, MWC Shanghai’s humanoid robot penalty shootout put embodied AI to the test
One of the biggest crowd-pullers at MWC Shanghai 2026 was a fully autonomous humanoid robot penalty shootout, rather than a smartphone launch or an AI keynote. Held over two days at the Shanghai New International Expo Centre, the competition drew more than 10,000 spectators as eight Chinese embodied AI teams battled through nearly 100 rounds […]
- Robotics startup FieldAI has hit a $100 million milestone
Robotics startup FieldAI has hit a $100 million milestone Business Insider
Score: 42🌐 MovesJun 26, 2026https://www.businessinsider.com/robot-startup-fieldai-achieves-100-m-milestone-in-revenue-contracts-2026-6 - Stanford scientists built an AI that can design healthier, greener burgers
Stanford researchers have developed BurgerAI, an AI system that creates healthier and more sustainable burger recipes without compromising on taste.
Score: 42🤖 ModelsJun 26, 2026https://www.digitaltrends.com/cool-tech/stanford-scientists-built-an-ai-that-can-design-healthier-greener-burgers/ - Authenticity, regulation, and authority in the age of AI
Authenticity, regulation, and authority in the age of AI EurekAlert!
- The Download: brain-melting heatwaves and unprecedented OpenAI restrictions
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Heat waves mess with your brain. Scientists are trying to figure out why. —Jessica Hamzelou It’s been hot in London this week. Really hot. A dangerous heat wave has hit Western…
Score: 41🌐 MovesJun 26, 2026https://www.technologyreview.com/2026/06/26/1139780/the-download-heatwaves-brain-health-openai-restrictions/ - Scale Robot Policy Evaluation with Ray
Scale Robot Policy Evaluation with Ray
Score: 41🌐 MovesJun 26, 2026https://www.anyscale.com/blog/distributed-sim-eval-robotics-ray-anyscale - The Real AI Safety Discussion That Just Isn’t Happening
If you spend any time watching the AI safety debate play out online, you’ve probably noticed it’s a bit of a circus. Right now, the conversation is totally dominated by tech investors pushing for maximum speed, software developers who think a few lines of code can solve anything, and click-hungry ... [continued] The post The Real AI Safety Discussion That Just Isn’t Happening appeared first on CleanTechnica .
Score: 41🌐 MovesJun 26, 2026https://cleantechnica.com/2026/06/25/the-real-ai-safety-discussion-that-just-isnt-happening/ - pgEdge joins rush to merge OLTP and OLAP storage to support AI
pgEdge joins rush to merge OLTP and OLAP storage to support AI InfoWorld
Score: 41🌐 MovesJun 26, 2026https://www.infoworld.com/article/4190042/pgedge-joins-rush-to-merge-oltp-and-olap-storage-to-support-ai.html - ‘The Daily’ and ‘The Opinions’: How A.I. Is Changing Loneliness and Taste
The story of a woman who let a robot into her home. Plus, a discussion about why Silicon Valley has taken such an interest in taste.
- Why Your GenAI Strategy Is Stalling, And How 'Article Scoring' Fixes It
To fix this, you need to treat knowledge quality exactly like financial risk or search engine optimization.
- Copperlane Raised $4.1 Million to Put an AI Loan Officer Inside America's Lenders
Copperlane Raised $4.1 Million to Put an AI Loan Officer Inside America's Lenders entrepreneur.com
- What AI-Native Companies Do Differently
What AI-Native Companies Do Differently Time Magazine
Score: 40🌐 MovesJun 26, 2026https://time.com/partner-content/charter/what-ai-native-companies-do-differently/ - Jiangsu's first AI-powered 10 Gbps all-optical campus network launched at Southeast University
PARTNER CONTENT: Integrating 50G-PON, FTTR-B, Wi-Fi 7, and intelligent AI scheduling to deliver 10 Gbps bidirectional speeds with ultra-low 0.1ms latency across Southeast University
- DropPR.ai Publishes Seven-Signal Framework for AI Source Readiness
DropPR.ai Publishes Seven-Signal Framework for AI Source Readiness USA Today
- AI in math: a convincing proof that is completely incorrect
Explores how AI-generated proofs can appear convincing yet be flawed, highlighting challenges in AI-assisted mathematics.
Score: 40🌐 MovesJun 26, 2026https://ioplus.nl/en/posts/ai-in-math-a-convincing-proof-that-is-completely-incorrect - Mediclinic Middle East recognised with five awards for healthcare excellence, global artificial intelligence and global sustainability
Mediclinic Middle East recognised with five awards for healthcare excellence, global artificial intelligence and global sustainability
- DTU and Esri India Join Hands to Advance GeoAI Education and Research
Esri India, the market leader in Geographic Information System (GIS) software, location intelligence, and mapping solutions in India, today announced the signing of a Memorandum of Understanding (MoU) with Delhi Technological University (DTU) to establish a Centre of Excellence (‘CoE’) in Geospatial Technologies with a focused thrust on GeoAI. The partnership marks a significant step […] The post DTU and Esri India Join Hands to Advance GeoAI Education and Research appeared first on CXOToday.com .
- Using AI in HR: Benefits, how to use it, and examples
Using AI in HR: Benefits, how to use it, and examples AI at Meta
- AI Face Aversion Goes Viral as 22 Billion Yuan AI Manga Market Hits Growth Ceiling
AI-generated faces trigger physiological aversion among users as China 22B yuan AI manga market confronts aesthetic fatigue and slowing growth
- Young Americans feel more threatened by AI than young Chinese. Why?
My four-year-old son has become fascinated with his new friend, who has endless patience and an answer for everything. She is an artificial intelligence assistant on Doubao, one of China’s most popular AI applications. My son, obsessed with space, black holes and galaxies, keeps asking Doubao for related videos. When the video is of low quality or inaccurate, I would stop it and explain it may not be reliable. Despite my concerns about AI-generated information, I let him interact with AI within...
- New Cooley platform provides AI legal help for startups
Built with legal AI startup Legora and trained on Cooley’s data, the platform will roll out to the summer batch of Y Combinator startups first.
Score: 40🌐 MovesJun 26, 2026https://www.semafor.com/article/06/26/2026/new-cooley-platform-provides-ai-legal-help-for-startups - Anthropic’s Mythos mess is only getting worse
The White House standoff could have dire implications for the US AI industry.
- AI Search Visibility Tools For Professionals Announced Amid ChatGPT Usage Trends
AI Search Visibility Tools For Professionals Announced Amid ChatGPT Usage Trends USA Today
- Run a vLLM Server on HF Jobs in One Command
Run a vLLM Server on HF Jobs in One Command
- Bored of reading papers? This AI tool turns them into TikTok-like videos
University of Washington researchers built PaperTok, an AI system that converts academic papers into short-form videos with editable scripts, storyboarded scenes, and author credits
Score: 39🌐 MovesJun 26, 2026https://www.digitaltrends.com/cool-tech/bored-of-reading-papers-this-ai-tool-turns-them-into-tiktok-like-videos/ - How PTOP's Synaptic Quant(TM) Works: AI Filters Market Noise, Identifies Catalysts, and Builds Complete Trade Plans for Retail Investors
How PTOP's Synaptic Quant(TM) Works: AI Filters Market Noise, Identifies Catalysts, and Builds Complete Trade Plans for Retail Investors USA Today
- Samsara Ride Along pushes fleet safety AI beyond incident flagging
Samsara’s Ride Along uses AI to review full driving sessions. Most fleet safety systems focus on individual incidents. The post Samsara Ride Along pushes fleet safety AI beyond incident flagging appeared first on FreightWaves .
- AI to reconstruct the diet of human ancestors (IMAGE)
AI to reconstruct the diet of human ancestors (IMAGE) EurekAlert!
- How to Chat With Your Codebase Locally and Privately, No Code Leaves Your Machine
The AI coding tools everyone uses are reading your proprietary code on someone else’s servers, and on a large codebase they still hallucinate functions and conventions they have no way of knowing. You can build a local assistant that actually understands your repository, answers questions about it in plain language, and never sends a single line off your machine. Here is why it is worth doing, the one detail that makes a code assistant good instead of useless, and exactly how to set it up. If you work on a real codebase, you have probably had this experience with an AI coding tool. You ask it about a function, and it confidently describes behavior that does not exist, invents an API your project never used, or ignores a convention your team has followed for years. It’s not being stupid. It simply has no reliable knowledge of your specific code, so when its context runs out, it fills the gap with a plausible guess. On a large repository this happens constantly, because the whole codebase doesn’t fit in the model’s context window, and the tool is working from fragments. There is a second problem sitting underneath the first, and for a lot of developers it’s the bigger one. When you use a hosted AI coding assistant, your code is being sent to a company’s servers to be processed. For a personal project that might not bother you. For proprietary code, a client’s repository, anything under an NDA, or work in a regulated field like finance, defense, or healthcare, it’s a real problem, sometimes a disqualifying one, and it’s why a lot of teams simply can’t use these tools on their most sensitive code. Both problems have the same fix. You can build a local assistant that indexes your entire codebase, answers questions grounded in your actual code rather than guesses, and runs entirely on your own machine, so not a single line is ever transmitted anywhere. It’s free after the hardware you already own, it works offline, and once it’s set up you can ask it things like where a function is used, what a module does, or how a pattern flows through the project, and get answers drawn from your real code. Here is why it works, the detail that makes or breaks it, and how to build it. Why your code needs more than a chatbot The reason a plain language model is unreliable on your codebase is simple. It was trained on a vast amount of public code, so it knows general patterns well, but it knows nothing about your specific repository, your internal conventions, your architecture, the function you wrote last week. Ask it about those and it is guessing from the general patterns it learned, which is exactly why it invents things. The fix is the same technique that powers a private document assistant, retrieval augmented generation, applied to code. Instead of relying on the model’s memory, you give it the relevant pieces of your actual codebase to read before it answers. Your code gets broken into pieces, each piece gets converted into a numerical fingerprint that captures its meaning and stored in a local index, and when you ask a question, the system finds the pieces most relevant to it, hands them to the model, and asks it to answer from those. The model stops guessing about your code and starts answering from it. That retrieval step, feeding it your real code instead of trusting its memory, is what turns a confident hallucinator into an assistant that actually knows your project. The detail that makes or breaks it, chunking code correctly Here is the part most tutorials skip, and it’s the single thing that separates a code assistant that works from one that is useless. How you break your code into pieces matters enormously, and the naive approach fails badly on code specifically. Most generic retrieval setups chop text into fixed-size blocks, say every 500 tokens, regardless of what the text is. That’s fine for prose. It’s a disaster for code, because it will cut a function in half, split a class from its methods, and separate a piece of logic from the context that explains it. When the system later retrieves one of those mangled fragments, it hands the model half a function with no beginning, and the answer is garbage. The fix is to chunk code along its natural boundaries. Instead of slicing by character count, you split by function, by class, by module, so each piece you store is a complete, meaningful unit, a whole function with its signature, a full class, a coherent block. This is often called function-aware or structure-aware chunking, and it’s the highest-impact decision in the whole build. A code assistant with good chunking and a modest model will run circles around one with a powerful model and code sliced into arbitrary fragments. If you take one thing from this guide, it’s that the quality of your code assistant is decided more by how intelligently you split the code than by which model you run. Two ways to build it There are two honest paths, and both keep your code entirely local. One needs almost no code, the other gives you full control. The first way is to use an existing tool that already does codebase retrieval, and for most developers this is the right answer. The standout is Continue, the open-source assistant that has become the de facto replacement for cloud coding tools and plugs straight into VS Code, JetBrains, and other editors. It has a codebase feature built in, you point it at your project and ask questions referencing your whole repository, and you configure it to run on local models so nothing leaves your machine. You define which local model handles chat, which handles autocomplete, and which handles the embeddings that power the code search, all in one config file. Other tools like Open WebUI and AnythingLLM offer similar repository indexing behind a chat interface. If you want the capability without building it, install one of these, point it at your local models, and you’re working. The second way is to build the pipeline yourself, which is the right choice when you want to control exactly how your code is chunked, indexed, and retrieved, or wire the assistant into your own tooling. The whole thing is a short pipeline you can write in a script, parse and chunk the codebase along function boundaries, embed each chunk with a local embedding model, store the vectors in a local database, and at query time retrieve the relevant chunks and hand them to a local model for the answer. The reason to do it yourself is the chunking, since building the pipeline lets you make that structure-aware splitting as smart as your codebase needs, which a packaged tool does not always expose. Either way, you need one tool underneath and the right pair of models. The setup, step by step Here is the whole build as a sequence you can follow. Install Ollama, the free tool that runs models locally. Download it from ollama.com for your system, and it serves models to whatever tool or script you point at it. Confirm it works with ollama — version in your terminal. Pull two models, and this is the detail people miss. A code assistant needs two different models, a chat or code model that writes the answers, and a separate embedding model that turns your code into the searchable fingerprints. They’re not the same thing. Pull both. The embedding model nomic-embed-text is small, fast even without a graphics card, and handles code well, and for the chat model a code-focused model is best. ollama pull nomic-embed-text # turns your code into searchable vectors ollama pull qwen2.5-coder:14b # the code model that answers (pick by hardware) 3. Choose your code model by your hardware. On a light machine, a small coder model works for basic help. On a typical developer machine with 16 gigabytes of memory, a 14-billion code model is a solid balance. On a strong desktop with a 24-gigabyte graphics card, a 30 to 33-billion coder model gives the best quality and gets close to the cloud tools on pure coding tasks. The current generation of code-focused models is genuinely strong at this size. ollama pull qwen2.5-coder:1.5b # light, also good for fast autocomplete ollama pull qwen3-coder:30b # strong desktop, best local code quality 4. Pick your path. For the tool route, install Continue in your editor, open its config, set your chat model, your autocomplete model, and nomic-embed-text as the embedding model, all pointed at Ollama, then use its codebase feature to ask questions across your project. For the build-it route, install a vector database like ChromaDB and write the index-then-query pipeline, making sure to chunk along function and class boundaries rather than by fixed size. 5. Index your codebase once, then ask. Point the tool or script at your repository and let it build the index, which takes anywhere from seconds to a few minutes depending on size. Then ask in plain language, where is this function called, what does this service do, how does data flow through this module, and the answers come back grounded in your actual code, with the relevant files in view. That’s the whole process, and your code never leaves your machine at any step. The honest tradeoffs This is genuinely useful, but it’s not a wholesale replacement for the best cloud tools yet, and you should know where the limits are. Smaller local models, under roughly 13 billion, hallucinate noticeably more on obscure APIs and edge cases, so for a private code assistant you want to run the largest code model your hardware comfortably holds. Local inference is also slower per token than a top cloud model, often several times slower, though the latency is near zero since there is no network round trip, so it feels more responsive than the raw speed suggests. And for the hardest agentic work, large multi-file refactors, complex multi-step planning, the best cloud models still lead, which is why many developers run a hybrid, local for sensitive or proprietary repositories where privacy is non-negotiable, and cloud for everything else. One practical security note, keep the local services bound to your own machine and do not expose their ports to the network, since the code index has no authentication of its own. None of that undercuts the core value. For understanding a codebase, locating functionality, onboarding to an unfamiliar project, and answering questions about your own code, a local assistant is genuinely capable, and it does it without sending your proprietary code to anyone. For the code you are not allowed to or do not want to upload, that’s not a compromise, it’s the only version that works at all. Why it is worth doing Set this up and you get the thing the cloud tools promise, an assistant that understands your codebase, without the two problems that come with them, the hallucinations from a model that doesn’t actually know your code, and the exposure of sending your code to someone else’s servers. The local version fixes both at once, it answers from your real repository because you fed it your real repository, and it keeps everything on hardware you control. The larger point is that this capability is no longer something only the big tools can offer. The pieces, a local model runner, a good embedding model, a vector store, and crucially the knowledge to chunk your code intelligently, are all free and available to you. Build it once, get the chunking right, and you have a private assistant that knows your codebase and tells no one about it. For anyone working on code that cannot leave the building, that’s not just convenient, it’s the difference between using AI assistance and being locked out of it entirely. If you build a local codebase assistant, drop a comment with the tool or stack you used, the models you settled on, and how you handled chunking, because the chunking strategy is where these setups live or die and the next builder will want to know what worked for you. How to Chat With Your Codebase Locally and Privately, No Code Leaves Your Machine was originally published in Towards AI on Medium, where people are continuing the conversation by highlighting and responding to this story.
- Everything is not okay with DuckDuckGo and its AI
DuckDuckGo's AI search assistant was tricked into repeating a fabricated story, highlighting how coordinated misinformation can fool modern AI systems.
- Resilience In The AI Era Starts With The Network You’ve Forgotten
To reduce risk from your AI program, address the gaps in your legacy infrastructure.
- Nianxiang Technology Raises Near-Million Angel Round for Neural Interface Wristband
Nianxiang Technology secures angel funding for Omniband, a non-invasive sEMG neural interface wristband targeting next-gen human-computer interaction
- The Learned Helplessness of Corporate Pride: How AI Tools Can Finally Hold Companies Accountable
New technology can give us a much clearer picture about which companies really support LGBTQ+ rights.
Score: 37🌐 MovesJun 26, 2026https://www.inc.com/fabrice-houdart/learned-helplessness-corporate-pride/91364962 - New AI Scams Are Targeting You, LastPass Was Breached Again, and an Urgent Warning for Apple Owners
New AI Scams Are Targeting You, LastPass Was Breached Again, and an Urgent Warning for Apple Owners PCMag
Score: 36🌐 MovesJun 26, 2026https://www.pcmag.com/news/new-ai-scams-are-targeting-you-lastpass-was-breached-again-and-an-urgent - We Gamified AI Adoption for Our Team. Here’s What We Learned.
Was it kind of cringe? Absolutely. But it also worked. Try these 5 things for your own program.
- Opinion | Government Isn’t Doing Better on AI Than on UFOs
Inspiring confidence about their ability to manage new risks? Not a strong suit of Biden or Trump.
Score: 35🌐 MovesJun 26, 2026https://www.wsj.com/opinion/government-isnt-doing-better-on-ai-than-on-ufos-789197a3?mod=rss_Technology