Writing · 170 posts
Notes from running a business alone, with AI
What I built, what it cost and what broke: AI tools, automation, hiring VAs and the business lessons behind them. Many are paired with a video on YouTube.
Latest
· 7 min
I let a local AI sort and tag forty thousand photos
A decade of unsorted photos, described and tagged by a vision model running on an old GPU, with nothing uploaded anywhere. How the pipeline works, what it misclassified, and what the whole thing costs to run.
Read · 7 min
How I choose a local AI model: a method that takes an hour
Leaderboards rank models on standardized tests, which says little about your specific task. The selection method I use for production work: define the job, narrow by hardware, then run a shortlist against a tiny test set built from your own real inputs.
Read · 8 min
Why local models slow down and the levers that fix it
Local model slowdowns trace back to a handful of predictable causes: context length, the KV cache, models spilling out of VRAM, and uncapped output. Here are the levers that fix them, in the order I actually check.
ReadAll posts
2026
- I let a local AI sort and tag forty thousand photosA decade of unsorted photos, described and tagged by a vision model running on an old GPU, with nothing uploaded anywhere. How the pipeline works, what it misclassified, and what the whole thing costs to run. · 7 min read
- How I choose a local AI model: a method that takes an hourLeaderboards rank models on standardized tests, which says little about your specific task. The selection method I use for production work: define the job, narrow by hardware, then run a shortlist against a tiny test set built from your own real inputs. · 7 min read
- Why local models slow down and the levers that fix itLocal model slowdowns trace back to a handful of predictable causes: context length, the KV cache, models spilling out of VRAM, and uncapped output. Here are the levers that fix them, in the order I actually check. · 8 min read
- Two years of local AI: what was hype and what was realTwo years of running models on my own hardware, scored promise by promise. Privacy and high volume economics held up, parity with the best cloud models did not, and the maintenance load is the cost nobody prices in. · 8 min read
- The overnight bill that made me give my AI agent a budgetAn agent stuck in a retry loop spent real money all night on a task it could never finish. Here is the counter, the cap, and the warning I built so that cannot happen again. · 7 min read
- I put AI code review on my own commits. Does it help?A few months of running a model over every diff I commit: the real bugs it caught, the context it cannot see, the noise it generates, and why the whole thing only works while it stays advisory. · 7 min read
- How AI reads my invoices without touching the moneyA small pipeline that pulls supplier, total, due date, and invoice number out of incoming invoices into a review sheet. It has no access to payments, and every row still gets approved by hand. · 6 min read
- The AI news digest that replaced my morning scrollI wired RSS feeds, a language model, and a schedule into a once-a-day news digest. What the build involves, what it costs each month, and where it still misses. · 7 min read
- I ran a local model on a mini PCA fanless mini PC with no graphics card runs a seven billion parameter model at ten to fifteen tokens per second. What the box cost, what I actually use it for, and where a small local model falls short. · 8 min read
- I spent a month testing an AI second brainFour weeks of routing all my notes through an AI recall layer. Plain language search and summarising earned a permanent place. The invented connections and the maintenance tax did not. · 7 min read
- I let an AI sort my inbox, and sorting is all it doesA small system reads every incoming email and files it as an action, a thing to know, or noise. It cannot send, delete, or reply, and that restriction is the reason the whole setup is trustworthy. · 7 min read
- How I monitor my servers with AI summariesA model reads thirty minutes of logs and metrics from my small fleet and writes a five sentence summary I can scan while making coffee. The alerting that can wake me up stays deterministic and never touches the model. · 7 min read
- The AI tools I actually use every dayFive AI tools survived a year of daily work: a writing model, one TTS voice, local image generation, a narrow agent, and plain scripts. What kept them around while dozens of others got dropped. · 6 min read
- I let an AI triage my messages, with one rule that never movesAn assistant reads my email and chat apps, sorts what matters, summarizes long threads, and drafts replies. It cannot send anything. Why that one boundary makes the whole setup workable. · 6 min read
- I put an AI on log watching dutyA cheap filter discards the routine lines, hard rules catch the known disasters, and a model reads only the ambiguous leftovers. What the layer costs, what it caught, and where I still refuse to trust it. · 7 min read
- An AI writes my changelogs nowCommit notes pile up in shorthand nobody else can read. A model turns that pile into a grouped, readable changelog in seconds, for a fraction of a cent, as long as I read every line before it ships. · 7 min read
- How my pipeline picks b-roll and draws diagrams from a scriptEvery visual in my faceless videos is placed by a program: footage matched to the meaning of each line, diagrams drawn from the structure of the script, captions taken from the text itself. Here is how the visual track gets assembled, and the ways it used to fail. · 7 min read
- Cron jobs plus AI quietly run my operationThe most useful AI I run has no chat window. It lives inside scheduled jobs that do real work overnight, from renders to backups to a morning summary. What each job does, and what happens when one breaks silently. · 7 min read
- How I back up everything automatically, and where AI actually fitsThe 3-2-1 backup system that runs nightly on my machines, built on deterministic tools like rclone. AI helps at the edges, writing configs and summarizing logs, and stays completely out of the copying. · 7 min read
- Building an AI agent with tools: how function calling actually worksA language model on its own cannot open a file, run a search, or send a message. Function calling is the mechanism that gives it hands, and it is simpler than the name suggests. · 7 min read
- The cheapest way to run AI at home depends on three costsHardware, electricity, and your own time are the three real costs of running models at home. Steady high volume favors local hardware you already own; spiky occasional use favors a metered API. · 7 min read
- Is CPU only AI usable? I timed it on a normal desktopI ran three model sizes on a six core desktop with thirty two gigabytes of RAM and no graphics card, timing the first word and the tokens per second. The small models handle real work; the seventy billion one worked and was useless. · 6 min read
- The dashboard I built to watch every automation I runHow I monitor dozens of scheduled jobs from one local status page. Every job pushes a tiny run record to a shared place, and the page flags anything that failed or went silent past its expected cadence. · 6 min read
- Do you actually need multiple AI agents?Multi agent diagrams look impressive, but every handoff costs money, time, and context. When one agent is enough, when parallel fan out wins, and why agent chains disappoint. · 7 min read
- Embeddings, explained with one pictureAn embedding is a list of numbers that places a piece of text on a map of meaning, and similar meanings sit close together. Here is the picture, the four step search recipe built on it, and the failure mode people forget. · 6 min read
- Fine-tuning vs prompting: when each is actually worth itPrompting costs minutes to iterate and covers most tasks. Fine-tuning changes the model's weights and leaves you with a dataset to keep current, so here is how I decide when it is actually worth it. · 6 min read
- The first things to delegate to a virtual assistantThe six tasks I handed to my assistant first, the audit that surfaced them, and the short list of things I will never delegate to anyone. · 8 min read
- Giving an AI agent memory that survives between runsA language model forgets everything when a run ends, so memory has to be built around it. The working version is a notes file read at the start and updated at the end, and the hard part is deciding what to forget. · 7 min read
- The guardrails I put around every AI agent I runAn agent with real tools can really send, delete, and spend. These are the specific limits I build around mine: least privilege, approval gates, dry runs, hard ceilings, and logs a human can skim. · 7 min read
- How AI tokens actually workA token is a chunk of text, usually a fraction of a word, and it is the unit behind AI pricing, paste limits, and the way long chats forget. One mental picture, a desk that fills up, explains all of it. · 7 min read
- How AI transcription works, and where it predictably failsA speech model turns audio into a grid of frequency features and predicts the likeliest word sequence behind them. That design explains both its accuracy on clean speech and its predictable failures on rare words and messy recordings. · 6 min read
- How context windows actually workA context window is the model's working memory, measured in tokens, and everything inside it costs money and latency. Here is what the headline numbers mean, where long contexts quietly fail, and the habits I use to keep mine short. · 7 min read
- How function calling works: the model only ever asksA language model can only produce text, yet AI assistants check weather and update calendars. The mechanism behind that is function calling, explained step by step. · 6 min read
- How I decide what to write aboutOne text file per brand, about sixty entries in the biggest, and I have written nine. Topic selection stops being a creative decision the moment you publish on a schedule. · 7 min read
- How I hire a Filipino VA on OnlineJobs.phThe full process I use to hire a virtual assistant through OnlineJobs.ph: one month on the paid plan, a specific job post with a hidden filter, a paid test task, and slow onboarding. · 8 min read
- How I use AI to write scripts that still sound like meMost of my video scripts start as AI drafts, and I rewrite every line before recording. Where the model genuinely helps, where it cannot help at all, and the read aloud test that decides what survives. · 7 min read
- How I write a VA job post that filters for the right peopleThe job post structure that took me from a flood of generic applications to about eighty genuinely good ones, section by section, including the one line that does most of the filtering. · 8 min read
- How to spot a VA scam before it costs youThe five red flags I watch for when hiring remote help, learned the hard way on my own first hire. Covers both directions, because employers burn workers too. · 7 min read
- I automated my email replies. The AI never touches sendAn agent reads the full thread, drafts a reply from templates I wrote myself, and stops there. Approval stays with me, and that one design decision is what the whole system depends on. · 6 min read
- How I automated my YouTube channel from one deskA walk through the pipeline that turns a two thousand word script into a finished video on my own hardware, what each stage costs, and the bugs I only caught by watching the output. · 7 min read
- I built an AI research agent to do my grunt workAn agent that reads full sources and returns a fixed-shape brief, cutting two hours of manual reading to about ten minutes per target. Here is how it is built and the one rule that makes it safe to use. · 6 min read
- I built a scraping system that runs itself, and the scraper is the smallest partFetch, parse, store, dedupe, notify: the loop behind a scraping system that feeds a real pipeline daily. The parsing code is a day of work; the plumbing around it is the actual engineering. · 8 min read
- The voice on my videos is a clone, and the line I hold on itHow I cloned my voice from a few minutes of audio, what the clone still gets wrong, and the consent line that decides every single use of it. · 6 min read
- What giving an AI real access to my computer taught meHow MCP lets a model call real tools on my machine, the near miss that almost sent a message on my behalf, and the read versus write line every tool now lives behind. · 6 min read
- I let an AI agent manage my calendar for a monthAn AI agent had read and write access to my calendar for a month. The drafting and slot finding were real wins, the autonomous writing was a mistake, and one near double booking set the rule I now follow. · 6 min read
- I let my VA use my AI toolsWhat happened when I gave my assistant access to the AI tools I use daily: the three tools I handed over, the guardrails, and where the combination still fails. · 8 min read
- Installing Ollama and running your first local modelThe full path from nothing to a working local model: install Ollama, pull a small model, chat with it offline, then call it from your own code through the local server. Includes the short troubleshooting list beginners actually need. · 7 min read
- How I keep AI agents reliable enough to trustAn agent that demos well and an agent you can leave running unattended are different machines. The difference is built from constraints: scope, tools, validation, confirmation gates, and logs. · 7 min read
- How I keep my AI costs under controlMy first serious month of AI usage ended in a surprise bill, and the cause was a stack of small habits rather than one leak. These are the specific changes that keep my token spend predictable now. · 7 min read
- Local image generation with SDXL on an old GPUEvery thumbnail on my channel comes off an SDXL family model running on a years-old graphics card: one to two minutes per image, no cost per attempt, nothing uploaded anywhere. The workflow, the three settings that matter, and where a paid service still wins. · 7 min read
- Managing a remote VA across time zonesThe rhythm and the small toolkit I use to work with an assistant many hours away: async by default, a daily handoff loop, and a standing rule for acting when I am offline. · 8 min read
- Modern AI on a seven year old GPU: what still worksMy daily AI work runs on a GTX 1080 Ti that is roughly seven years old. What it still handles well, where it clearly fails, and the handful of tricks that decide the difference. · 7 min read
- My local LLM stack: what runs on the box and what still goes to an APIOne previous generation consumer GPU, a small rotation of open models, and a short set of routing rules that decide which tasks stay on the machine. The honest version, limits included. · 6 min read
- Fully offline AI meeting notesI replaced cloud meeting notes tools with a two stage pipeline on my own machine: local speech to text, then a local language model that writes the summary and action items. The recording never leaves the computer. · 6 min read
- How I onboard and train a new VA in a weekThe week-one process I use with every new assistant: scoped access on day one, screen recordings that become written procedures, one task at a time, and a daily check-in that tapers off. · 6 min read
- I built a content engine that runs many brands from one configOne shared pipeline engine, one small config file per brand, and a template every brand inherits from. How the architecture works, the discipline that keeps it clean, and when it is overkill. · 6 min read
- One pipeline, many channels: how I run several brands from one engineSeveral faceless channels come out of one shared engine plus one small config file per brand. What is shared, what stays unique, the separation rules that stop collisions, and the shared risk nobody warns you about. · 7 min read
- Building a private offline chatbot over your own documentsThe lookup-then-answer architecture behind a document chatbot that runs entirely on your own machine, plus the retrieval failures that cause wrong answers and the fixes that make it trustworthy. · 7 min read
- How prompt caching cut my AI billMy bill was climbing because every call re-sent the same two pages of instructions at full price. Prompt caching cut that workload's cost by more than half, and the fix took one afternoon of prompt reordering. · 6 min read
- Prompt engineering is overratedAfter a year of shipping real work with LLMs, the exact wording of a prompt turns out to be a minor variable. Context, examples, tools, feedback, and model choice move results far more. · 6 min read
- Quantization levels explained: what Q4, Q5, and Q8 actually trade awayThe number in a quant label is bits per weight, and it sets the whole trade between memory and quality. Rough VRAM figures per level, where the loss shows up first, and the decision rule I use on an 11GB card. · 7 min read
- Queues and schedulers are the backbone of my automationsThe layer that keeps my AI automations trustworthy is a job queue, a scheduler, and four plain patterns: idempotency, locks, retries, and a landing place for failed jobs. The first version of mine took an afternoon to write. · 7 min read
- RAG explained by building one over my own notesI built a retrieval augmented generation system over my own notes to understand what the term actually means. This is the full build, step by step, plus the failure modes that showed up and the cases where you should skip RAG entirely. · 7 min read
- Why I replaced my no code automations with scripts and a local modelThe per task bills kept climbing and every broken automation meant guessing at someone else's black box. I moved the ones that mattered to small scripts with a local model handling the one judgment step, and left the simple ones alone. · 7 min read
- How I route work between three AI modelsThe small dispatch layer that sends each AI task to the cheapest model that can handle it. What it cut from my bill, how the fallback works, and the three ways the idea can quietly cost you instead. · 7 min read
- Running a business from anywhere with a small VA teamWhat actually makes location freedom work: a few trusted people, written procedures with clear owners, and the honest costs that never make it into the pitch. · 7 min read
- Running AI locally versus paying for APIs, a year into bothWhere running models on your own card genuinely wins, where the hosted APIs quietly win, and the time costs that never make the thumbnail. Includes the per task rule I use to place each job. · 6 min read
- The self hosted AI assistant I keep running around the clockA small local model, a pile of single job scripts, a scheduler, and a chat surface I can reach from my phone. What the assistant does on a normal day, how hard questions get routed out to a paid API, and the reliability work that keeps it alive. · 7 min read
- Starting an automated content channel from zero in 2026If I had to rebuild my automated channel with nothing, I would rent every tool, pick an uncomfortably narrow niche, and ship a four step pipeline before buying any hardware. The order that avoids the mistakes that cost me the most time. · 7 min read
- Structured output from LLMs: turning prose into data you can trustModels answer in friendly paragraphs while pipelines need exact shapes. The path runs from asking nicely to schemas to constrained decoding, with validation catching what still slips through. · 7 min read
- The Telegram bot that runs my automationsHow a small Telegram bot became the remote control for my whole setup. The message loop, the single user ID check, confirmations for anything destructive, and the categories I deliberately kept off it. · 7 min read
- Text to speech in 2026: what makes a synthetic voice convincingEvery narration on my channel is synthetic, so the voice has to hold up for ten minutes at a stretch. Here is what separates convincing text to speech from robotic output, and the thousand word test I run before trusting any voice. · 7 min read
- Vector databases explained without the hypeWhat embeddings actually are, what a vector database does with them, and when a local library beats a dedicated server. Covers the failure modes that really bite: weak embeddings, stale indexes, and outgrowing your architecture. · 7 min read
- VRAM math: how to know what fits before you downloadA model that fits in VRAM runs fast, and a model that spills to the CPU crawls. The short arithmetic for weights, context, and overhead that predicts which side of that line any model lands on for your card. · 7 min read
- What actually breaks AI automationsField notes from a couple of years of running AI automations daily. The five real failure modes I keep hitting, none of them dramatic, and the building habit that turns quiet week-long breakage into loud second-long breakage. · 6 min read
- What I pay my virtual assistantsReal ballpark rates for remote assistants, how I structure hourly versus monthly pay, and the payment habits that decide whether good people stay. · 7 min read
- What I would automate first if I started overStarting from zero, I would build four things in a fixed order: a script for one daily annoyance, automated backups, a scheduler, and a single narrow assistant. The order carries the lesson. · 7 min read
- What my AI automations actually save meRoughly eight to twelve hours of repetitive work handed to scripts each week, against a tool bill in the low tens of dollars and an upkeep tax nobody invoices. The honest ledger, including the months where the whole thing ran at a loss. · 6 min read
- What my faceless video pipeline actually costs to runA stage-by-stage cost breakdown of a daily faceless video pipeline that renders locally: script generation in pennies, a metered voice charge per video, and the hardware, power, and maintenance time that never appear on a bill. · 6 min read
- When an AI agent beats a plain script (and when it does not)A working decision rule for choosing between an AI agent and a plain script, from someone who runs both daily. If you can write the steps down in advance, a script wins. · 7 min read
- Why AI streams its answers word by wordThe word by word reveal in a chat window is the model generating text in real time, one token after another. Here is why generation works that way and what the stream gives you once you build on these models. · 6 min read
- Wiring Claude into my real tools: the unglamorous realityWhat it actually takes to connect an AI model to your files, messaging, and automations. The model is the easy part; the descriptions, credentials, and scoping are the real work. · 7 min read
- Local text-to-speech vs paid voice APIs: how I decideI generate voiceovers constantly, so local versus paid TTS is a monthly bill and a quality call on every project. Where local voices stand now, where paid still wins, and the volume math behind the choice. · 6 min read
- What I would do differently if I started this business overOne unit of my hardware costs about ten dollars a month to run. Three decisions I would repeat, four I would change, and why a retrospective written by the person who knows the ending is worth less than it sounds. · 7 min read
- How I set up a new machine (and the nine days I did not plan for)A blank Windows install to a finished render took four hours and ten minutes. Finding what lived only on the old machine took nine more days. The order I install in now. · 7 min read
- Transcribing audio locally with Whisper: the whole workflowI transcribe hours of audio every week on a GPU I own, with Whisper. Model sizes, timed output, transcript cleanup, and the failure modes worth knowing before you trust the result. · 6 min read
- The AI tools I dropped this year, sorted by whyA screenshot reader spent three minutes on my fleet dashboard and returned numbers that were not on the screen. Five reasons tools left my setup, sorted by reason because the reasons generalise. · 7 min read
- When local AI is the wrong choiceI run most of my AI workloads on hardware I own and still pay a cloud bill every month. These are the tasks where local models lose, and the routing questions I use to decide. · 7 min read
- What thirty automations actually cost me in a yearLogging every minute spent keeping existing jobs alive came to eleven hours in one quarter, and nothing broke that quarter. Here is where the time goes and the four rules I use to cap it. · 7 min read
- Running a business from one laptop and six serversHow I actually run a multi-brand operation across one laptop and six servers, and where AI agents fit into that setup without the hype. · 6 min read
- The automation I rebuilt three timesWhy an automation that worked on day one still needed three rebuilds, and what that says about running AI agents in production instead of in a demo. · 6 min read
- What I check before trusting an AI answerA practical checklist from someone running AI agents in production every day: how I decide when an AI answer is safe to act on and when it needs verification. · 5 min read
- Building a word list for what AI mishearsHow I built a running word list to catch the transcription corrections speech-to-text keeps needing, and how it plugs into a real content pipeline. · 6 min read
- Buy or build now that code is cheapAI coding agents have made writing software faster than ever, which changes the buy vs build calculation. Here's a practical framework for deciding, from someone who runs both every day. · 6 min read
- Can you do this without learning to codeA straight answer on how much automation you can build without programming, where no-code tools stop working, and when learning to code actually pays off. · 6 min read
- Do I tell people AI helped write this?An honest breakdown of when and how I disclose AI involvement in my writing and videos, and why the question is messier than a simple yes or no. · 5 min read
- Exporting my data before I need itA practical case for exporting your own data on a schedule, before a vendor migration, account lockout, or shutdown forces the issue. · 5 min read
- Getting a second opinion when you work aloneHow to use AI as a second opinion when you have no coworkers to check your work, and where that setup actually breaks down. · 6 min read
- How I keep fifteen brands from sounding the sameEleven of my fifteen brands were opening every article on a number followed by a failure. Here is the editorial system that pulled them apart, and the part of the sameness I decided to keep. · 7 min read
- How long my automation projects actually takeA real breakdown of automation project timelines from someone who builds and runs them daily, including why the model call is never the bottleneck. · 6 min read
- One instruction doc for a person and a modelWhy maintaining separate instructions for your VA and your AI agent creates drift, and how to write a single SOP that both a person and a model can actually follow. · 6 min read
- Paying for AI tools from another country: what actually happens to your cardA practical look at what happens when you pay for AI subscriptions and API credit from outside the vendor's home country: currency conversion, declined cards, regional pricing, and business billing. · 6 min read
- Sharing logins with a VA without handing over everythingA practical breakdown of how to give a virtual assistant real access to your accounts without handing over your master password, your email, or your entire digital identity. · 6 min read
- Single points of failure in a one person businessA practical look at where solo AI-run operations actually break, and how to build in redundancy without slowing yourself down. · 6 min read
- The dry run mode that lied to meWhy dry run mode in AI and automation pipelines can pass clean and still fail for real, and what I changed after it burned me. · 6 min read
- The messages I never let AI answerWhy I keep AI out of certain customer replies, even after running automation in production every day. A practical line for where AI customer replies help and where they don't. · 5 min read
- The naming rules that hold my systems togetherA practical naming convention for AI agents, scripts, and automation pipelines, built from running local and cloud AI in production every day. · 6 min read
- The physical failures that broke my softwareA field guide to hardware failure symptoms that get misdiagnosed as software bugs, from an operator who runs local AI automation daily. · 6 min read
- The runbook that runs my systems without meHow I turned scattered scripts and habits into a written runbook that lets AI agents operate my infrastructure while I sleep, and where the guardrails are. · 5 min read
- The spreadsheet that outlived three automationsWhy a flat file workflow keeps beating custom automation for tracking work, and when it actually stops being enough. · 6 min read
- The work AI made worseA production operator's honest look at the tasks AI actually degraded, not the hype cycle version, from someone running agents and local models every day. · 6 min read
- The work I delegated and took backA rundown of what happened when I handed real production tasks to AI agents, what broke, and which jobs I pulled back to run myself. · 5 min read
- Video SOPs rot faster than written onesWhy a screen recording of your process goes stale in weeks while a written standard operating procedure survives interface changes. What actually breaks and how to structure both. · 6 min read
- What I never paste into a chat windowAn operator's working rules for AI data privacy: what never goes into a cloud chat window, why, and how local models and agent tooling change the calculus. · 6 min read
- What one more brand actually costs to runA breakdown of what adding another brand really costs once you count the automation, the render time, and the hours nobody puts on a spreadsheet. · 6 min read
- When a model changes without telling youModel behaviour drift is what happens when the AI model behind your pipeline changes quietly. Here's how it shows up in production and how to catch it before it breaks something. · 6 min read
- When a platform suspends you with no appealWhat actually happens when a cloud AI platform, API provider, or hosting account gets suspended with no appeal path, and how to build automation that survives it. · 6 min read
- When two of my automations fought each otherA concrete walkthrough of how two unrelated automations ended up undoing each other's work, why it took a while to notice, and what actually fixed it. · 5 min read
- When Your VA Starts Using AI QuietlyYour VA is probably already using ChatGPT to draft your emails and reports. Here's how to tell, why it matters, and how to set rules instead of getting surprised. · 6 min read
- Where the free tier is actually enoughA practical look at which free AI tools hold up under real, daily use and where the limits force an upgrade. · 6 min read
- Which alerts I muted and what it costA concrete account of alert fatigue in a production AI automation stack: which alerts got muted, why it felt reasonable at the time, and what broke as a result. · 5 min read
- Who Maintains the Code an AI Wrote?AI can generate working code in seconds, but someone still has to own it long after the prompt is gone. Here's what maintaining AI generated code actually looks like in production. · 6 min read
- Why I dictate more than I typeAn operator's honest look at building a dictation workflow into daily AI automation work, including where voice beats typing and where it still falls short. · 5 min read
- The AI advice everyone repeats that I think is wrongSix AI positions I get argued with about, each grounded in something that broke in a business I run: a nine month old prompt that outlived two model swaps, and a ten step chain correct six times in ten. · 7 min read
- What AI actually costs me in a monthEvery voiceover I publish is synthesised on a free tier and costs nothing per call, while an annual plan I have never used runs until March 2027. Here is where the money in an AI-assisted business actually goes, sorted by how each cost behaves. · 7 min read
- The automation I deleted (and why the business got better)Nine scheduled jobs came off my servers last year and nothing broke. Here is how I decide which automation is an asset and which one is quietly costing me more than doing the work by hand. · 7 min read
- I built a content pipeline that runs itself, and here is what brokeA dry run marked an entire publish queue as shipped in about eleven seconds without sending a thing. That bug, and four other failure classes, cost me far more than building the pipeline did. · 8 min read
- Running AI on an eight year old GPU: what actually worksAn 11GB GTX 1080 Ti is only about two times behind a current flagship at generating tokens, but five to ten times behind at reading your prompt. That gap decides what old hardware is good for. · 7 min read
- Building A Weekly Report That Reads Itself Into My InboxHow I built an automated weekly report pipeline that pulls my own data, summarizes it with an AI step, and lands in my inbox every Monday without me touching it. · 6 min read
- How I Keep A Year Of Automation Logs SearchableA practical breakdown of how I store, structure, and search a year's worth of AI automation logs without a cloud logging bill, using JSONL files and a small SQLite index. · 6 min read
- How I Split Work Between A VA And An AutomationA practical breakdown of va versus automation: how I decide what goes to a human assistant and what gets handed to a script, agent, or local model. · 6 min read
- How I Version And Roll Back My Automation ConfigsA practical look at how I track changes to my AI automation configs with git, and the rollback habits that keep a broken workflow from becoming a lost afternoon. · 6 min read
- What I learned running the same prompt across three model sizesA practical look at comparing AI model sizes, from a small local model to a mid-size and large cloud model, and what changes as parameter count goes up. · 6 min read
- Managing a Remote Virtual Assistant Across Time ZonesThe rhythm and tools I use to manage a remote assistant across a big time-zone gap - async by default, a daily handoff, and judging outcomes over hours. · 7 min read
- Running a Business From Anywhere With a Virtual Assistant TeamThe real reason I can run my business from anywhere is not a laptop-lifestyle trick - it is a small, trusted remote team, systems, and letting go. Here is how. · 7 min read
- How to Onboard and Train a New Virtual Assistant in a WeekMy exact onboarding process for taking a new VA from day one to genuinely useful in about a week - scoped access, record-then-document, SOPs, and feedback. · 7 min read
- How to Spot a Virtual Assistant Scam Before It Costs YouThe real red flags when hiring a remote assistant, on both sides of the table, and the boring reliable way to protect yourself and the honest workers. · 7 min read
- How to Write a VA Job Post That Gets Great ApplicantsThe exact anatomy of a virtual assistant job post that attracts great applicants instead of a flood of the wrong ones - specifics, pay, and a hidden filter. · 7 min read
- OnlineJobs.ph vs Upwork vs Fiverr: Where I Actually HireI have hired real people on all three. They solve different problems. Here is what each is best for, the honest cost math, and a simple rule for choosing. · 7 min read
- I Gave My Virtual Assistant My AI Tools: Here's What HappenedThe popular take is that AI replaces virtual assistants. I did the opposite - I gave my assistant my AI tools. Here is how the combination actually works. · 7 min read
- What to Delegate to a Virtual Assistant (and What I Never Would)A practical delegation playbook - the delegation audit, the first tasks I handed over, how to hand a task over so it sticks, and what I keep for myself. · 7 min read
- How Much to Pay a Virtual Assistant (Real Numbers From My Experience)What I actually pay my virtual assistants, with real ballpark ranges, how I structure pay, and why paying fairly is also the smart business move. · 7 min read
- How to Hire a Virtual Assistant on OnlineJobs.ph (My Exact Process)The exact step-by-step process I use to hire great Filipino virtual assistants on OnlineJobs.ph - the job post, filtering, a paid test task, the interview, and paying fairly. · 5 min read
2024
- How much time does it take to make a 25 second tiktok video?How much ROI can I expect from running Facebook/Tiktok advertisement campaign?negative ROI. 0 if you are lucky. majority of the guys running ads lose money on the first sale. they can do that because they can get you to pay them for · 5 min read
- How much time does it take to make a 25 second tiktok video?Most of the time when you ask this question, you already have an idea in mind, perhaps you have seen someone else doing it before. if this is the case, it · 2 min read
- Vietnam’s Richest Man – The Rise of Pham Nhat VuongIf you have been reading all the books you can find on the biographies of business persons, then you would have found that most of these examples are from · 3 min read
- Why are my video views on Tiktok so low? am i being shadowbanned?What is a shadowban? a shadowban means your account is under a “shadow” punishment, and you are getting a heavy reduction of your views on your recent · 2 min read
- Does the Facebook Pixel help? Shall i let it collect more data to mature?this applies to the google/facebook/tiktok/whatever new network pixel. It does not help The only the pixel helps in, is to help track conversion or action · 3 min read
- Tiktok July 2022 physical meetup event – We were NOT invitedIt has been about 3 years since Tiktok launched a physical meeting event in Singapore. I think that physical bonding is important to build the · 5 min read
- 5 Misconceptions of self-care: How self-care really looks like.In this article, we will be talking about the 5 common misconceptions about self-care and how does self-care look like. I consider this as the biggest · 4 min read
- Personal Development: Expectations vs. RealityHave you ever felt stuck in your life? Have you ever questioned your capabilities? Have you ever wondered what to do in your bewildering life and thought · 6 min read
- Why you should go the extra mile(Managing Efforts as a Student, Worker, and a human being) As a Student Everyone started as a student. You go to school early in the morning and do · 5 min read
- 15 years of thinking I had an attitude problemFrom sleeping on my school desk to 4 trips to A&E in 2017. What fixing my sleep took, what didn't work, and why I protect my evenings now. · 2 min read
- Why do we take so many camera or excessive multiple takes with the same camera?You may notice that we take footage using 4-5 cameras at the same time. As for one of the brochures, I believe we took more than 10 takes. This is because · 1 min read
- why do you keep posting the same video? is it not spam?any one video is only shown to a very small group of people, maybe 50, or 500 if you have a small account. most of the videos dont go viral. maybe 1 out · 1 min read
2023
- Why you should speak English?The Importance of English Proficiency: A Gateway to Global OpportunitiesIntroduction: In an increasingly interconnected world, the ability to communicate effectively has become a crucial skill. One language that has emerged as · 4 min read
- Why you should write a business planPersonally, I have written more than 20 business plans in order to seek funding. I failed terribly, but the knowledge of writing business plans have given · 5 min read
- Blue Ocean Strategy – How I applied it to develop a product in Ally MediaIntroduction to the Blue Ocean Idea This is one of the popular books that took me a while to pick up because I felt like there was no such thing. I was · 11 min read
- Difference between Singapore and other countries culturesI think of taiwan culture as a go getter culture. They wake up early, take initiative, work long hours and are willing to do more for the same reward. · 2 min read
- How long do I need to create organic content on Tiktok before I see results?The quick answer is 3 years. We managed to do it for ourselves in about 1.5 years. Some people with high ticket items can take up to 5 years. How long did · 7 min read
- How much ROI can I Expect from running Facebook/Tiktok advertisement campaigns?negative ROI. 0 if you are lucky. majority of the guys running ads lose money on the first sale. they can do that because they can get you to pay them for · 5 min read
- How much time does it take to make a 25 second tiktok video?Most of the time when you ask this question, you already have an idea in mind, perhaps you have seen someone else doing it before. if this is the case, it · 2 min read
- Vietnam’s Richest Man – The Rise of Pham Nhat VuongIf you have been reading all the books you can find on the biographies of business persons, then you would have found that most of these examples are from · 3 min read
- Why you should hire online?Nowadays, many companies are hiring talents from other countries. I am not talking about work from home, where maybe you go down to office once a week. I · 4 min read
- Product #3 – Marks and Spencer Stretch Woven BeltFor those who have a large tummy, this is a god send. One of the most common problems I have is that it’s very hard to keep the pants in place. as I walk · 1 min read
- Product #1 – Panasonic Portable Water Flosser, 2-Speed Battery-Operated Oral Irrigator with Collapsible Design for Travel – EW-DJ10-WAmazon link Taobao link I put on braces sometime around 2020, and I noticed that food will always get stuck between the braces and the teeth. This will · 3 min read
- Product #5 – portable power bank – different variations · 1 min read
- Product #2 – Small portable water flask for taking medicineI usually take my medicine sometime around 730pm. And sometimes I am outside. So I need to keep some water with me. the other bottles are either too big · 1 min read
- Product #4 – Stop Bad Breathe with Dr Tung’s Tongue ScraperDo you know anyone with bad breathe? It’s hard to tolerate the smell. But the solution is surprisingly easy. Most of the odor producing gunk is on the · 1 min read
- Why you should use Taobao and how to use itThere are alot of new marketplaces and we are spoiled for choice. whats the difference? I think the first marketplace platform Singaporeans are familiar · 2 min read
No posts match that. Try a shorter word.