Loading today’s stories
Leadership1 distinct publisher3 min readUpdated
A Platformer columnist ranks an LLM-maintained personal wiki above every app in the annual productivity roundup. The pilot cost is weeks of attention, not procurement.
The Board Room · Leadership desk
Compiled by The Board RoomSomething wrong?How this is made
At the beginning of April, the AI researcher Andrej Karpathy posted that he had been finding it very useful to use LLMs to build personal knowledge bases for topics of research interest [1]. Because Karpathy is closely followed online and coined the term "vibe coding," the web filled up within hours with GitHub repos, YouTube videos and Substack posts explaining how to build one [3][4].
The mechanics are unglamorous. Source documents go into a local folder, and an LLM extracts and organizes their contents into a Markdown wiki that gets updated as new material is added [2]. Read the component list closely and there is no vendor in it: a folder, a model you already pay for, and plain text files [1]. That matters for anyone who has spent a quarter waiting on security review and seat-count negotiations before a team could try anything.
The interesting data point is not the technique but the ranking. In its annual productivity column, Platformer reports that of everything tried this year to get better at the deskbound parts of the job, the LLM wiki has easily been the most useful [5]. The three tools that survived from previous years are all commercial products: the launcher Raycast, the note app Capacities, and Recall [10]. So the top-rated change of the year was a workflow, while the durable furniture was purchased software [2].
The column is honest about the bill. The columnist calls the idea an infohazard and says it consumed several weeks of building with no idea whether it would help at all [8]. It requires a fair degree of maintenance, compared in the piece to a vintage sports car, and there are almost certainly easier ways to build a personal knowledge base [6]. The recommendation is conditional: worth the time if your work has made you crave a good research assistant [7].
Notice what the surviving tools actually do. Capacities holds a daily journal plus tagged news links from Techmeme, so clicking a tag like "Labor" surfaces everything saved on that subject over a couple of years [12][13]. Recall's remaining use is a Chrome extension that produces near-instant text summaries of YouTube videos, replacing hours of podcast listening [14]. Raycast's paid tier adds quick AI searches inside the launcher, and it is now available on Windows as well as macOS [11]. The payoff in every case is retrieval of material the person already encountered, not generation of new material [3].
Two caveats a manager should hold onto. This is one person's account, and the columnist discloses that their fiance works at Anthropic [16]. And the piece's own test for whether a tool works is longevity: does it get installed on a new machine, does the subscription get renewed, can you point to where it saves time [9].
That test is the thing to watch. The wiki is the centerpiece of a post that has run in 2023, 2024 and 2025 [15], so the useful signal arrives next year, when we learn whether the wiki was still being maintained or quietly abandoned. If you pilot it, measure two numbers: hours of setup and upkeep per person, and whether anyone other than the builder can find an answer in it.
Follow any of these and your For You feed starts watching them — no settings page required.
Ranked by verification strength, evidence, and original report placement.
The columnist writes that of everything tried this year to get better at the deskbound parts of the job, the LLM wiki has easily been the most useful.
At the beginning of April, AI researcher Andrej Karpathy tweeted: "Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest."
Karpathy described his process as adding source documents to a local folder and using an LLM to extract and organize their contents into a Markdown wiki that gets updated as he adds new material.
Karpathy's AI-related pronouncements are closely followed online, and he coined the term "vibe coding."
Seemingly within hours of the post, the web filled up with GitHub repos, YouTube videos and Substack posts about how to set up an LLM wiki.
The columnist writes that, like a vintage sports car, the LLM wiki requires a fair degree of maintenance, and that there are almost certainly easier ways to create a personal knowledge base.
Evidence-backed comparisons of source perspectives and observed adoption signals. Read the methodology
Which Builder, Operator, and Investor concerns the observed source mix emphasized—not a truth score.
Evidence, demonstrated adoption, hype gap, incentives, and confidence are assessed independently, each on its own current evidence. How these are measured.
One self-reported practitioner account
All claims trace to a single first-person column. The mechanics of the setup and the tools retained are described precisely and consistently, and the origin claim (Karpathy's post) is quoted, but there is no measurement, no second observer and no independent verification of the productivity result.
One documented desk plus unquantified community how-tos
Concrete adoption is one practitioner running the wiki plus a multi-year retained stack of three apps. Wider uptake is asserted only as a burst of GitHub repos, videos and posts with no counts, and Raycast's Windows release is the single distribution datapoint.
Slightly overstated: superlative from a sample of one
The 'most useful tool of the year' framing generalizes a single desk's experience, and the diffusion claim rests on impressions rather than counts. The overstatement is modest because the source itself supplies the counterweights: weeks of setup, ongoing maintenance, easier alternatives, and a narrow conditional recommendation.
Disclosed household tie to a model lab; recurring tool-recommendation format
The column discloses that the writer's fiance works at Anthropic, and the format is an annual roundup that names and recommends specific paid products, which creates a mild promotional pull. No affiliate, sponsorship or vendor relationship with the named tools is disclosed or evident, and the disclosure is prominent, which limits the score.
Internally consistent but unreplicated
The account is detailed, self-consistent and openly hedged, so the descriptive facts about the setup and tool stack are reliable. Confidence in the transferable conclusion, that an LLM-maintained Markdown wiki is the highest-value AI tool for knowledge work, stays moderate because it rests on one unreplicated self-report.
leadership
Every's 30 people, four products and one cloned editor: the self-driving company in practice1 distinct publisher
invest
Canva guided 2026 growth down to 20%. The worse detail is who never got asked.1 distinct publisher
build
Claude Desktop already ships the schema for handing meeting follow-ups to agents1 distinct publisher
product
Pocket's export window closed and the demand went shopping1 distinct publisher
Distinct publishers with included, body-backed reporting in this cluster.
1 article · August 18, 2026