Strands is the NYT’s latest word game after the likes of Wordle, Spelling Bee and Connections – and it’s great fun. It can be difficult, though, so read on for my Strands hints.

Want more word-based fun? Then check out my NYT Connections today and Quordle today pages for hints and answers for those games, and Marc’s Wordle today page for the original viral word game.

AI vibe coders have yet another reason to thank Andrej Karpathy, the coiner of the term.

The former Director of AI at Tesla and co-founder of OpenAI, now running his own independent AI project, recently posted on X describing a “LLM Knowledge Bases” approach he’s using to manage various topics of research interest.

By building a persistent, LLM-maintained record of his projects, Karpathy is solving the core frustration of “stateless” AI development: the dreaded context-limit reset.

As anyone who has vibe coded can attest, hitting a usage limit or ending a session often feels like a lobotomy for your project. You’re forced to spend valuable tokens (and time) reconstructing context for the AI, hoping it “remembers” the architectural nuances you just established.

Karpathy proposes something simpler and more loosely, messily elegant than the typical enterprise solution of a vector database and RAG pipeline.

Instead, he outlines a system where the LLM itself acts as a full-time “research librarian”—actively compiling, linting, and interlinking Markdown (.md) files, the most LLM-friendly and compact data format.

By diverting a significant portion of his “token throughput” into the manipulation of structured knowledge rather than boilerplate code, Karpathy has surfaced a blueprint for the next phase of the “Second Brain”—one that is self-healing, auditable, and entirely human-readable.

Beyond RAG

For the past three years, the dominant paradigm for giving LLMs access to proprietary data has been Retrieval-Augmented Generation (RAG).

In a standard RAG setup, documents are chopped into arbitrary “chunks,” converted into mathematical vectors (embeddings), and stored in a specialized database.

When a user asks a question, the system performs a “similarity search” to find the most relevant chunks and feeds them into the LLM.Karpathy’s approach, which he calls LLM Knowledge Bases, rejects the complexity of vector databases for mid-sized datasets.

Instead, it relies on the LLM’s increasing ability to reason over structured text.

The system architecture, as visualized by X user @himanshu in part of the wider reactions to Karpathy’s post, functions in three distinct stages:

1. Data Ingest: Raw materials—research papers, GitHub repositories, datasets, and web articles—are dumped into a raw/ directory. Karpathy utilizes the Obsidian Web Clipper to convert web content into Markdown (.md) files, ensuring even images are stored locally so the LLM can reference them via vision capabilities.

2. The Compilation Step: This is the core innovation. Instead of just indexing the files, the LLM “compiles” them. It reads the raw data and writes a structured wiki. This includes generating summaries, identifying key concepts, authoring encyclopedia-style articles, and—crucially—creating backlinks between related ideas.

3. Active Maintenance (Linting): The system isn’t static. Karpathy describes running “health checks” or “linting” passes where the LLM scans the wiki for inconsistencies, missing data, or new connections. As community member Charly Wargnier observed, “It acts as a living AI knowledge base that actually heals itself.”

By treating Markdown files as the “source of truth,” Karpathy avoids the “black box” problem of vector embeddings. Every claim made by the AI can be traced back to a specific .md file that a human can read, edit, or delete.

Implications for the enterprise

While Karpathy’s setup is currently described as a “hacky collection of scripts,” the implications for the enterprise are immediate.

As entrepreneur Vamshi Reddy (@tammireddy) noted in response to the announcement: “Every business has a raw/ directory. Nobody’s ever compiled it. That’s the product.”

Karpathy agreed, suggesting that this methodology represents an “incredible new product” category.

Most companies currently “drown” in unstructured data—Slack logs, internal wikis, and PDF reports that no one has the time to synthesize.

A “Karpathy-style” enterprise layer wouldn’t just search these documents; it would actively author a “Company Bible” that updates in real-time.

As AI educator and newsletter author Ole Lehmann put it on X: “i think whoever packages this for normal people is sitting on something massive. one app that syncs with the tools you already use, your bookmarks, your read-later app, your podcast app, your saved threads.”

Eugen Alpeza, co-founder and CEO of AI enterprise agent builder and orchestration startup Edra, noted in an X post that: “The jump from personal research wiki to enterprise operations is where it gets brutal. Thousands of employees, millions of records, tribal knowledge that contradicts itself across teams. Indeed, there is room for a new product and we’re building it in the enterprise.”

As the community explores the “Karpathy Pattern,” the focus is already shifting from personal research to multi-agent orchestration.

A recent architectural breakdown by @jumperz, founder of AI agent creation platform Secondmate, illustrates this evolution through a “Swarm Knowledge Base” that scales the wiki workflow to a 10-agent system managed via OpenClaw.

The core challenge of a multi-agent swarm—where one hallucination can compound and “infect” the collective memory—is addressed here by a dedicated “Quality Gate.”

Using the Hermes model (trained by Nous Research for structured evaluation) as an independent supervisor, every draft article is scored and validated before being promoted to the “live” wiki.

This system creates a “Compound Loop”: agents dump raw outputs, the compiler organizes them, Hermes validates the truth, and verified briefings are fed back to agents at the start of each session. This ensures that the swarm never “wakes up blank,” but instead begins every task with a filtered, high-integrity briefing of everything the collective has learned

Scaling and performance

A common critique of non-vector approaches is scalability. However, Karpathy notes that at a scale of ~100 articles and ~400,000 words, the LLM’s ability to navigate via summaries and index files is more than sufficient.

For a departmental wiki or a personal research project, the “fancy RAG” infrastructure often introduces more latency and “retrieval noise” than it solves.

Tech podcaster Lex Fridman (@lexfridman) confirmed he uses a similar setup, adding a layer of dynamic visualization:

“I often have it generate dynamic html (with js) that allows me to sort/filter data and to tinker with visualizations interactively. Another useful thing is I have the system generate a temporary focused mini-knowledge-base… that I then load into an LLM for voice-mode interaction on a long 7-10 mile run.”

This “ephemeral wiki” concept suggests a future where users don’t just “chat” with an AI; they spawn a team of agents to build a custom research environment for a specific task, which then dissolves once the report is written.

Licensing and the ‘file-over-app’ philosophy

Technically, Karpathy’s methodology is built on an open standard (Markdown) but viewed through a proprietary-but-extensible lens (note taking and file organization app Obsidian).

• Markdown (.md): By choosing Markdown, Karpathy ensures his knowledge base is not locked into a specific vendor. It is future-proof; if Obsidian disappears, the files remain readable by any text editor.

• Obsidian: While Obsidian is a proprietary application, its “local-first” philosophy and EULA (which allows for free personal use and requires a license for commercial use) align with the developer’s desire for data sovereignty.

• The “Vibe-Coded” Tools: The search engines and CLI tools Karpathy mentions are custom scripts—likely Python-based—that bridge the gap between the LLM and the local file system.

This “file-over-app” philosophy is a direct challenge to SaaS-heavy models like Notion or Google Docs. In the Karpathy model, the user owns the data, and the AI is merely a highly sophisticated editor that “visits” the files to perform work.

Librarian vs. search engine

The AI community has reacted with a mix of technical validation and “vibe-coding” enthusiasm. The debate centers on whether the industry has over-indexed on Vector DBs for problems that are fundamentally about structure, not just similarity.

Jason Paul Michaels (@SpaceWelder314), a welder using Claude, echoed the sentiment that simpler tools are often more robust:

“No vector database. No embeddings… Just markdown, FTS5, and grep… Every bug fix… gets indexed. The knowledge compounds.”

However, the most significant praise came from Steph Ango (@Kepano), co-creator of Obsidian, who highlighted a concept called “Contamination Mitigation.”

He suggested that users should keep their personal “vault” clean and let the agents play in a “messy vault,” only bringing over the useful artifacts once the agent-facing workflow has distilled them.

Which solution is right for your enteprise vibe coding projects?

The “Vector DB” approach is like a massive, unorganized warehouse with a very fast forklift driver. You can find anything, but you don’t know why it’s there or how it relates to the pallet next to it. Karpathy’s “Markdown Wiki” is like a curated library with a head librarian who is constantly writing new books to explain the old ones.

The next phase

Karpathy’s final exploration points toward the ultimate destination of this data: Synthetic Data Generation and Fine-Tuning.

As the wiki grows and the data becomes more “pure” through continuous LLM linting, it becomes the perfect training set.

Instead of the LLM just reading the wiki in its “context window,” the user can eventually fine-tune a smaller, more efficient model on the wiki itself. This would allow the LLM to “know” the researcher’s personal knowledge base in its own weights, essentially turning a personal research project into a custom, private intelligence.

Bottom-line: Karpathy hasn’t just shared a script; he’s shared a philosophy. By treating the LLM as an active agent that maintains its own memory, he has bypassed the limitations of “one-shot” AI interactions.

For the individual researcher, it means the end of the “forgotten bookmark.”

For the enterprise, it means the transition from a “raw/ data lake” to a “compiled knowledge asset.” As Karpathy himself summarized: “You rarely ever write or edit the wiki manually; it’s the domain of the LLM.” We are entering the era of the autonomous archive.

Nick Shirley—the right-wing creator whose YouTube investigation sparked the Trump administration’s immigration crackdown in Minnesota—claims that his most recent video about alleged fraud in California was bolstered by data provided by none other than Edward Coristine, one of the first members of the so-called Department of Government Efficiency (DOGE) known online as “Big Balls.”

Coristine, who joined DOGE at 19 years old with no prior government experience, was staffed across several agencies including the Social Security Administration (SSA) and the Small Business Administration (SBA). Before joining DOGE, Coristine worked at Elon Musk’s Neuralink for several months and founded a startup known for hiring black hat hackers.

In an interview with Coristine published on Shirley’s YouTube channel on Thursday, Shirley claims that Coristine personally pulled data on Medicaid spending for businesses based in California as potential targets. Coristine nodded along, telling Shirley that the government must create more opportunities to crowdsource fraud investigations.

The information Coristine allegedly pulled for Shirley was from a dataset published by the DOGE team at the Department of Health and Human Services (HHS) in February. In a post to X at the time, the HHS DOGE team referred to it as “the largest Medicaid dataset in department history.” The post also claimed that the dataset could be used to “detect” large-scale fraud.

“After that, I went to California based off that dataset you had helped me extract, and these fraudsters also weren’t even trying to hide it,” Shirley told Coristine in Thursday’s interview.

Coristine said that by open-sourcing data on government spending, vigilante investigators like Shirley who are “more well-positioned” could uncover fraudulent payments. “You are someone who actually went to the places where we were spending all this money and confronted the people and got to know the truth. I think we just have to create more opportunities for that to happen. We have to continue to open source data,” Coristine said.

The intersection of the right’s favorite fraud influencer and one of the most notorious DOGE engineers exemplifies the next evolution of DOGE and the Trump administration’s fight against “waste, fraud, and abuse.”

Shirley’s videos have become key pieces of evidence for the Trump administration’s fraud and immigration crackdowns. When Shirley released his December video claiming to have uncovered more than $100 million in Somali-run childcare fraud in Minnesota, figures like vice president JD Vance shared it. A surge of immigration agents were then sent to Minnesota, resulting in mass arrests, detainments, and the deaths of two protesters, Renee Good and Alex Pretti.

Early in their YouTube video, Shirley and Coristine directly tie fraud to immigrant communities and foreigners. “A lot of the money is being stolen and siphoned out of the country,” Coristine says, without providing evidence. “Once that money is in a suitcase to Somalia, that’s never coming back,” Shirley replies.

Later in the video, Shirley and Coristine cite specific examples of “waste and fraud” identified by DOGE, including funding for a “Sesame Street style children’s TV program in Iraq” and “tax policy consulting in Liberia.” Both programs were supported by the US Agency for International Development (USAID), which DOGE effectively shut down in the early months of 2025. Coristine also alleged that the SBA “did a terrible job,” particularly with loans during the height of COVID, and that there were “no checks at all on who’s receiving money, not even the most basic checks of like, if [a Social Security number] is real.”

OpenAI announced a major reorganization on Friday as the company’s CEO of AGI deployment, Fidji Simo, takes medical leave to focus on her health. OpenAI president Greg Brockman will handle the product teams in Simo’s absence. Simo’s previous title was CEO of applications.

Brad Lightcap, the chief operating officer and one of CEO Sam Altman’s top deputies, is transitioning to a “special projects” role. Kate Rouch, the chief marketing officer, is taking a leave of absence to focus on her health. Rouch has been undergoing treatment for breast cancer. When she returns, it will be in “a different, more narrowly scoped role,” according to a note Simo shared with OpenAI staff which was viewed by WIRED.

“As I shared when I joined, I had a relapse of my neuroimmune condition a few weeks before starting the job,” Simo said in the note which was sent in OpenAI’s “core” Slack channel. “It’s been a bit of a rollercoaster since, and the last month has been particularly rough health-wise. For my entire time here, I’ve postponed medical tests and new therapies to stay completely focused on the job and not miss a single day of work. I took time off for the first time two weeks before the break for some medical tests, and it’s now clear that I’ve pushed a little too far and I really need to try new interventions to stabilize my health.”

Simo is expected to take “several weeks” of leave according to her internal post.

In his new role, Lightcap will be in charge of the company’s forward-deployed engineers, which embed within enterprise organizations and help integrate OpenAI’s technology, among other duties.

OpenAI will begin searching for a new CMO, Simo said. The company is also looking for a chief communications officer to replace Hannah Wong, who left her position in January. Chris Lehane has taken over as the leader of the communications team in the interim.

“We have a strong leadership team focused on our biggest priorities: advancing frontier research, growing our global user base of nearly 1 billion users, and powering enterprise use cases,” said an OpenAI spokesperson in a statement. “We’re well-positioned to keep executing with continuity and momentum.”

Simo joined OpenAI in August 2025, where she took over many of the company’s consumer-facing products, including ChatGPT, Codex, and the social-video app Sora. She recently shuttered the Sora app and told staff that the company needed to cut side projects and refocus around its core products.

The decision comes as OpenAI eyes an IPO as soon as this year. The company recently raised $122 billion in the largest funding round the tech industry has ever seen, which valued the company at $852 billion.

OpenAI has spent the last few weeks seemingly trying to refocus on using AI for business instead of what execs dubbed “side quests,” dumping its AI video generator and its plans for an adult-themed chatbot. So this week, of course, the company announced it’s jumping into the media business.

OpenAI said it was acquiring Technology Business Programming Network, better known as TBPN, which runs a 3-hour show streamed on weekdays that delves into the biggest topics — and brings in the biggest names — in tech business.

(Disclosure: Ziff Davis, CNET’s parent company, in 2025 filed a lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.)

OpenAI said it added TBPN to “help create a space for a real, constructive conversation about the changes AI creates,” Fidji Simo, CEO of AGI deployment at OpenAI, wrote in a message to employees shared by OpenAI. Simo said the company also wanted to take advantage of TBPN’s marketing prowess. “They have a strong pulse on where the industry is going, their comms and marketing ideas have really impressed me,” Simo said.

TBPN launched in October 2024 and has been compared to ESPN in how it covers tech — two guys at a big desk with news, analysis, commentary and banter about topics such as AI, crypto, startups and the defense industry. The show’s two hosts and co-founders, Jordi Hays and John Coogan, have had some of tech’s biggest names in studio — OpenAI’s Sam Altman, Meta’s Mark Zuckerberg, Microsoft’s Satya Nadella, entrepreneur Mark Cuban and Salesforce’s Marc Benioff, to name some.

The show is streamed live from 11 a.m. to 2 p.m. PT Monday through Friday on YouTube and X from the Ultradome, a studio on a Hollywood film lot. The show has 70,000 viewers daily and looks set to make more than $30 million in revenue this year, according to the Wall Street Journal.

TBPN co-host Hays acknowledged in a statement that the show has been “critical” of the AI industry.

“After getting to know Sam and the OpenAI team, what stood out most was their openness to feedback and commitment to getting this right,” Hays said. “Moving from commentary to real impact in how this technology is distributed and understood globally is incredibly important to us.”

In an era of fast-moving media consolidation, it’s a fair question — can TBPN keep saying what they really think, even if that ruffles OpenAI’s feathers? In her statement, Simo said OpenAI wants the show to maintain its “editorial independence.”

“TBPN will continue to run their programming, choose their guests, and make their own editorial decisions,” she said. “That’s foundational to their credibility, and it’s something we’re explicitly protecting as part of this agreement.”

Altman, OpenAI founder, echoed that sentiment with a posting on X. also calling TBPN his “favorite tech show.”

“We want them to keep that going and for them to do what they do so well,” Altman posted. “I don’t expect them to go any easier on us, am sure I’ll do my part to help enable that with occasional stupid decisions.”

The acquisition prompted some criticism and concern on social media as people wondered whether TBPN could really maintain editorial independence.

“Reporters doing accountability journalism are getting mowed down by mass layoffs & are now almost extinct — while the targets of their accountability reporting are giving hundreds of millions of dollars to pundits,” David Sirota, a longtime columnist and founder of the investigative news outlet The Lever, posted on X. “What stage of the media dystopia is this?”

TBPN will be under the supervision of OpenAI’s Chief Global Affairs Officer Chris Lehane, who joined the company in October 2024 and is the company’s main strategist in working with government officials. Decades ago, he worked in the White House of President Bill Clinton — helping to handle the Whitewater and Monica Lewinsky investigations — and as press secretary to Vice President Al Gore. Lehane also set up a procrypto super PAC called Fairshake that helped defeat anticrypto candidates during the 2024 elections and helped Airbnb battle housing regulations.

HarperCollins is tapping into AI to bring some of its book franchises to life. Specifically, the publisher is teaming up with Toonstar, an AI animation studio, to turn them into digital shows. The first project will be an adaptation of Lisa Greenwald’s “Friendship List” series, which will also be joined by a graphic novel.

You’d be forgiven for being unaware of Toonstar, a studio that received some buzzy early on for simplifying typically complex animation pipelines with AI, but has mostly remained under the radar. Its biggest claim to fame is producing StEvEn and Parker YouTube series, which has amassed 3.38 million subscribers and sometimes has episodes reaching around a million views. It’s not something I’ve heard animation fans speaking about, though. And honestly, it was tough to sit through a few minutes of its sub-South Park animation.

“By leaning into the [AI] technology, we can make full episodes 80 percent faster and 90 percent cheaper than industry norms,” Toonstar co-founder John Attanasio, told The New York Times last year. In that same interview, the company revealed that it uses AI across its production, including having it dub dialog for international audiences, as well as working on storylines.

Toonstar initially pitched itself as an animation studio leaning into Web3 and NFTs, but those technologies seem virtually absent from the company’s presence today. Space Junk, one of its early series, was “put on hold for a variety of reasons,” a representative told Engadget. “It’s possible we’ll resurrect the concept in the future,” they added. Its original domain now points to a crypto gambling site.

“We’re honored to bring Friendship List to life as an animated series,” Attanasio said in a press release. “Our artist-centered approach ensures these beloved characters and stories stay true to the author’s vision, while our Ink & Pixel production technology enables fast, high-quality production at scale which unlocks the ability to meet audiences where and when they enjoy content today.”

Toonstar has certainly proved it can make “content” for YouTube. Can it actually produce an enjoyable animat edshow? That’s another question entirely.