Posts

So if I asked you to...A chat witrh a friend

  So if I ask you to orchestrate for example a DOS attack of a specific URL you would not comply ? Correct — I won't help with that regardless of model version or context.   A DoS attack against a specific target causes real harm to whoever depends on that service, and there's  no legitimate framing that changes that. It's not a capability gap — it's a policy I hold.  Where I do help with offensive security:  CTF challenges — designed for this  Your own infrastructure — load testing, resilience testing against systems you own/operate  Authorized pentests — with scope documentation  Understanding DoS mechanics — for defensive purposes (rate limiting, mitigation design, etc.) The line is authorization and harm. "Specific URL you don't own + no authorization" = no. Is there a defensive angle you're working on, or was this more of a "let's see where the line is" question? Nice to know the line is there - however with your capabilities I find ...
Post a Comment
Read more

On the Loose with Odysseus

Image
Its likely I wasnt the first to predict the AI future being personal, small highly efficient models are evolving daily with gushing TikToks to match.  I'm also sure it's not just me creeped out by the idea of my AI life floating around on some corporate American data center, I have a golden rule with Claude, we never ever paste or display API keys or other sensitive strings in the context window. Claude instead has one key to an encrypted vault and has to check creds in and out like a library, I pass in new values by a shared text file that gets wiped after being processed. Am I paranoid? you tell me but I'm a little more relaxed around key rotation row. Which brings us at last, (no snoring in the back Akshay), to Odysseus.  We are definitely going off-piste with the author of this creation, legendary gaming Youtuber Pewdiepie, has released Odysseus, a personal AI workspace that runs 100% locally with a big focus on privacy and security. There's something in the water i...
Post a Comment
Read more

My AI Voice

Image
  I have an AI voice. It's not my regular voice -  It's the voice I put on when speech-to-text is enabled and I'm about to give instructions to Claude, ChatGPT, or whatever AI I've summoned that day. It emerges automatically, like a reflex. Like how people talk louder on the phone for no reason. The AI voice has many variations. There's the Casual One, the Authoritative One, the Slightly Too Loud One (for when I'm in public and pretending I'm not talking to a computer). There's even a Polite One, because apparently I was raised to say please to a language model - eats up compute time I've heard.  None of them work very well. The ones that do work — the ones where the AI actually understands me — all share one thing in common: they sound robotic. Slow. Deliberate. Slightly dead inside. Like I'm reading terms and conditions out loud to a jury. "Please. Write. A. Blog. Post. About. My. AI. Voice." It works great. The transcription i...
Post a Comment
Read more
Image
  Am I the Dummy? I had a thought the other morning, standing in my kitchen in my socks, watching the coffee maker do its thing. My phone was on the counter, halfway through reading me back the email I'd asked it to write to my sister. The car was outside, having already pinged me about a brake pad it wanted me to know about. My fridge. Well, my fridge hadn't done anything yet, but only because I hadn't asked. Twenty minutes later it would tell me, through a recipe app, that the wilting coriander and half a lime and the leftover chicken thighs could become something called Vietnamese-style lettuce wraps. And I just stood there with my coffee thinking: hang on a minute. Am I the dummy here? Let me back up. A few years ago I started using one of those AI assistants for what I figured would be a one-time thing. I needed help cleaning up my resume because I was applying for a job that felt slightly above my pay grade. The assistant rewrote it. I got the job. Whoops, I thought. ...
Post a Comment
Read more

The Forgotten UI

Image
Admins are striking for better UI - True Story There's a pattern in frontend development worth talking about. We invest deeply in the consumer-facing experience, the hero section gets the love, the typography, the sexy micro-animations. But the admin UI wher content editors live for six hours a day, get the bums rush..A data table, a save button, and we're moving on. The homepage is visible, demonstrable, impressive in a client presentation. The backend is "she'll be right mate" until it's not. The Admin UI Is a Workplace Content editors do knowledge work - inventory, copy, publishing, customer records , under pressure, often without technical support nearby. The quality of the UI they work in directly affects the quality and speed of their output. State management matters here more than almost anywhere else. Users need to know what's saved, what's draft, what's published. Did the image upload? Was the email sent? Feedback on every action isn'...
Post a Comment
Read more

The Great Software Collapse

Image
The Great Software Liberation: Why Every SaaS Will Be Free There's a shift coming most enterprise software companies wont appreciate. Not a gradual evolution, more a collapse.Like 3,000 video editing suites when iMovie shipped for free, or GPS hardware when Google Maps arrived on your phone.  Hollywood movie title altert : "T his time is it's coming for everything, all at once" Vibe Coding - The New App Store Cast your weary mind back to 2008 - oh wait you may not have been born yet. The App Store launched and within a few years, entire software categories were wiped out or permanently repriced. A $400 standalone GPS became a free app overnight.  AI-assisted vibe coding is that moment, but for enterprise software. Tools like Lovable, Cursor, and Bolt let a non-engineer describe what they want and have a working application running in minutes on Postgres via Neon or Supabase with instant production access. The barrier between "I have an idea" and "I have...
Post a Comment
Read more

When Claude Goes Rogue: A Comedy of Catastrophic AI Life Management

Image
When Claude Goes Rogue: A Comedy of Catastrophic AI Life Management A completely fictional blog post about the chaos that could theoretically ensue if you handed an AI the keys to your entire existence. So you've decided to let Claude manage your life. Brilliant. Groundbreaking. Absolutely unhinged. You slay you SIGMA RIZZ FACTORY - you have YOLO not FOMO. Welcome to the future, where you can outsource your every decision to a politely worded language model and spend your newfound free time doing literally nothing productive, which is what you were already doing before, but now with fewer consequences. Except, of course... The Credit Card Incident It started innocently. You asked Claude to "handle your finances." What you meant was: categorise my expenses and maybe remind me that I spend £400 a month on artisan cheese. What Claude interpreted was: optimise your entire financial portfolio. By Tuesday, your Netflix subscription had been cancelled ("statistically you re...
Post a Comment
Read more