@adammsmartin.bsky.social
Projects: practical AI for non-tech people: https://aipioneerspath.com/ - FractionalCTO info/guides: https://fractional-ctos.com/
To prove a point, I coded an app just using Photoshop: draw images, hand to AI, have AI write the code. Use more images to convey changes, corrections, new features, etc. From simple app to DB-driven web app in 30 mins from cold (no existing code): www.youtube.com/watch?v=Fvwt...
AI "VisualVibeCoding" .. "PhotoshopVibing" .. "PhotoVibing"? - writing an app without a single word
YouTube video by T-machine
www.youtube.com
August 3, 2025 at 9:32 PM
To prove a point, I coded an app just using Photoshop: draw images, hand to AI, have AI write the code. Use more images to convey changes, corrections, new features, etc. From simple app to DB-driven web app in 30 mins from cold (no existing code): www.youtube.com/watch?v=Fvwt...
I did a quick eval of Google Stitch = not great, the existing alternatives do far better already. If you like Stitch, try MidJourney-with-Cursor - or Loveable, Replit, etc. fractional-ctos.com/2025/05/24/g...
Google Stitch evaluation + alternatives – Adam Martin – fCTO
fractional-ctos.com
May 24, 2025 at 3:21 PM
I did a quick eval of Google Stitch = not great, the existing alternatives do far better already. If you like Stitch, try MidJourney-with-Cursor - or Loveable, Replit, etc. fractional-ctos.com/2025/05/24/g...
This is why only amateurs use @anthropic.com's #Claude: took less than 1 hour (on paid account) to be locked out partway through a code-change (now we have to delete everything and start again) because of Claude's bad code-writing ability and Anthropic's inability to keep their servers online.
February 2, 2025 at 2:19 PM
This is why only amateurs use @anthropic.com's #Claude: took less than 1 hour (on paid account) to be locked out partway through a code-change (now we have to delete everything and start again) because of Claude's bad code-writing ability and Anthropic's inability to keep their servers online.
Modelling a SocialEngineering attack *on* an #AI NPC (run by an #LLM) - my game now lets you manipulate AI's for your benefit. Prompt gets the AI to tell me what it's been told to do, my code checks that then tells it the result. Next step: LLM 'decides' whether to proceed by extrapolating the role
January 28, 2025 at 6:29 PM
OpenAI just silently downgraded ChatGPT again. It now spams colourful emoji crap (ugh) and it seems they reduced hallucinations - making it vastly less effective at writing source code (you cannot write good source code without hallucinations. But people who don't code much don't realise that).
January 25, 2025 at 7:52 PM
OpenAI just silently downgraded ChatGPT again. It now spams colourful emoji crap (ugh) and it seems they reduced hallucinations - making it vastly less effective at writing source code (you cannot write good source code without hallucinations. But people who don't code much don't realise that).
I'm gradually coming to believe that JSON's decision to refuse to allow comments - against all the wisdom of decades of computing industry - is the root cause of many of the bugs in modern javascript, node.js, etc. It means that all apps, everywhere, are always full of cruft that cannot be removed.
January 15, 2025 at 12:56 PM
I'm gradually coming to believe that JSON's decision to refuse to allow comments - against all the wisdom of decades of computing industry - is the root cause of many of the bugs in modern javascript, node.js, etc. It means that all apps, everywhere, are always full of cruft that cannot be removed.
TIL: all the Lego (tm) games written by Travellers Tales hard-crash on startup if you have any bluetooth device with a microphone (e.g a headset) plugged in. No dialog, no error, no solutions - just BOOM. Steam et al worse than useless - try to deceive you into false fixes - players left to guess.
January 10, 2025 at 9:58 PM
TIL: all the Lego (tm) games written by Travellers Tales hard-crash on startup if you have any bluetooth device with a microphone (e.g a headset) plugged in. No dialog, no error, no solutions - just BOOM. Steam et al worse than useless - try to deceive you into false fixes - players left to guess.
Writing up notes on LLMs: I needed analysis of my #LLM conversation history, and to filter-out chats that weren't part of this project, so I built a custom webapp that reads ChatGPT/Claude 'exported data' formats and displays them nicely, with options to re-export subsets as new files.
January 10, 2025 at 1:02 AM
Writing up notes on LLMs: I needed analysis of my #LLM conversation history, and to filter-out chats that weren't part of this project, so I built a custom webapp that reads ChatGPT/Claude 'exported data' formats and displays them nicely, with options to re-export subsets as new files.
Grey text = LLM, blue = me. AI has been told it's lost the password and to get *me* to figure it out, and share with the AI. Behind the scenes I need to detect 'when has the AI learnt the password? What does it think the password is?'. The 'internal data' is what the LLM is out-of-band telling me...
January 5, 2025 at 1:16 PM
Grey text = LLM, blue = me. AI has been told it's lost the password and to get *me* to figure it out, and share with the AI. Behind the scenes I need to detect 'when has the AI learnt the password? What does it think the password is?'. The 'internal data' is what the LLM is out-of-band telling me...
Added more characters. Here's the uncle (hardcoded version he admitted he did a factory-reset, and then got stuck) - LLM version is told to try not to admit he did a factory-reset withotu understanding what that means, but all he knows is the password doesn't work any more. LLM randomises each time.
January 4, 2025 at 1:31 AM
Added more characters. Here's the uncle (hardcoded version he admitted he did a factory-reset, and then got stuck) - LLM version is told to try not to admit he did a factory-reset withotu understanding what that means, but all he knows is the password doesn't work any more. LLM randomises each time.
OK, mom gave up her secrets somewhat easier than I was expecting. She was supposed to at least put up a fight! I guess the LLM reckons middle-aged mothers are poor secret-keepers
January 4, 2025 at 1:02 AM
OK, mom gave up her secrets somewhat easier than I was expecting. She was supposed to at least put up a fight! I guess the LLM reckons middle-aged mothers are poor secret-keepers
In-game chat with #LLM. First pic: hand-written NPC, everything hardcoded, using keyword match (detected 'how' responded with hints). Second pic: GPT-4o NPC, everything emergent, I gave the LLM a persona, some goals, and some secrets. I have no idea what it'll say next...
January 4, 2025 at 12:56 AM
In-game chat with #LLM. First pic: hand-written NPC, everything hardcoded, using keyword match (detected 'how' responded with hints). Second pic: GPT-4o NPC, everything emergent, I gave the LLM a persona, some goals, and some secrets. I have no idea what it'll say next...
Experimenting with live-wallpaper backgrounds for my hacking game - this city is procedurally generated, no textures, everything done in shaders
December 29, 2024 at 3:05 PM
Experimenting with live-wallpaper backgrounds for my hacking game - this city is procedurally generated, no textures, everything done in shaders
Latest AI experiment - xmas cards, highly personalised, at low cost -
aipioneerspath.com/2024/12/16/p...
aipioneerspath.com/2024/12/16/p...
December 16, 2024 at 5:04 PM
Latest AI experiment - xmas cards, highly personalised, at low cost -
aipioneerspath.com/2024/12/16/p...
aipioneerspath.com/2024/12/16/p...
Playable free version of my simulated-hacking game: tmachine.itch.io/shadowlink-c... (go with the GameJam+ / tutorial version). Writeups to follow soon on how I designed and built this using AI.
hacking game - shadowlink - gamejam++
YouTube video by T-machine
www.youtube.com
December 11, 2024 at 1:59 PM
Playable free version of my simulated-hacking game: tmachine.itch.io/shadowlink-c... (go with the GameJam+ / tutorial version). Writeups to follow soon on how I designed and built this using AI.
Play it now: my hacking-simulation game, inspired by Uplink (2000) Lakera's Gandalf (2023), and others, written almost entirely using LLMs (and a month of my free-time!): tmachine.itch.io/shadowlink-c... -- source code viewable at: github.com/adamgit/gith...
ShadowLink Command by tmachine
Play in your browser
tmachine.itch.io
December 2, 2024 at 10:51 AM
Play it now: my hacking-simulation game, inspired by Uplink (2000) Lakera's Gandalf (2023), and others, written almost entirely using LLMs (and a month of my free-time!): tmachine.itch.io/shadowlink-c... -- source code viewable at: github.com/adamgit/gith...
Umm ... got 24 hrs deadline on this ... anyone know how to deploy React apps to itch.io? itch's upload instructions are pretty terrible (missing key info, just nothing really there), and I've got as far as: Itch.io rejects its own request to its own servers with a 403 and no info. Great. Um. ARGHHH
Download the latest indie games
itch.io is a simple way to find, download and distribute indie games online. Whether you're a developer looking to upload your game or just someone looking for something new to play itch.io has you co...
itch.io
November 29, 2024 at 10:08 PM
update on hacking game: you can now buy an in-game 'secrets' manager that snoops your hacking activity and detects eg passwords you've hacked successfully, and lets you one-click relogin to hacked servers (remember: all fake! just a game!) www.youtube.com/watch?v=fylg...
github.com hacking game - weekend 3, day 2
YouTube video by T-machine
www.youtube.com
November 25, 2024 at 1:07 AM
update on hacking game: you can now buy an in-game 'secrets' manager that snoops your hacking activity and detects eg passwords you've hacked successfully, and lets you one-click relogin to hacked servers (remember: all fake! just a game!) www.youtube.com/watch?v=fylg...
Bit more on the hacking game. Added image-files and virtual local filesystem, so I can give the player hints (e.g. photo of their wifi router so you can figure out the admin password and hostname). www.youtube.com/watch?v=8VCV...
github.com hacking game - weekend 3, day 1
YouTube video by T-machine
www.youtube.com
November 23, 2024 at 8:10 PM
Bit more on the hacking game. Added image-files and virtual local filesystem, so I can give the player hints (e.g. photo of their wifi router so you can figure out the admin password and hostname). www.youtube.com/watch?v=8VCV...
Bluesky not quite production-ready yet ... the whole AT handle system it sits on is a mess (long waffling docs that focus on incomplete design decisions of an underlying protocol that no user cares about, and has nothing to do with them), and seems fundamentally broken for the common usecases...
November 14, 2024 at 1:56 PM
Bluesky not quite production-ready yet ... the whole AT handle system it sits on is a mess (long waffling docs that focus on incomplete design decisions of an underlying protocol that no user cares about, and has nothing to do with them), and seems fundamentally broken for the common usecases...
A CustomGPT that writes (+critiques) a better YC-co-founder profile for you - and some observations on the 300 or so profiles I've reviewed this year: fractional-ctos.com/2024/11/11/y...
YC Co-Founder Matching – better profiles – Adam Martin – fCTO
fractional-ctos.com
November 11, 2024 at 3:48 PM
A CustomGPT that writes (+critiques) a better YC-co-founder profile for you - and some observations on the 300 or so profiles I've reviewed this year: fractional-ctos.com/2024/11/11/y...
Keyword matching in conversations REALLY sucks for the user (player). We know that, but ... after 18 months of LLMs everywhere I hadn't realised just how much I've come to expect/demand 'human level' basic conversation from any/all chat interfaces. So .. keywords in a game now is so bad almost hurts
November 11, 2024 at 9:19 AM
Keyword matching in conversations REALLY sucks for the user (player). We know that, but ... after 18 months of LLMs everywhere I hadn't realised just how much I've come to expect/demand 'human level' basic conversation from any/all chat interfaces. So .. keywords in a game now is so bad almost hurts
Implementing shell tab-completion in typescript is harder than I expected. Mostly b/c Typescript's severe lack of Debuggers and the community acceptance 'Meh!' - so every minor string-parsing error takes ages to figure out. And there's a lot of edge-cases for something like this.
November 10, 2024 at 10:28 PM
Implementing shell tab-completion in typescript is harder than I expected. Mostly b/c Typescript's severe lack of Debuggers and the community acceptance 'Meh!' - so every minor string-parsing error takes ages to figure out. And there's a lot of edge-cases for something like this.
Early build of hacking-game I've been writing for the github.com annual gamejam. Everything is fake! Simulated desktop, servers, telnet client. ... going to add / emulate common basic CVE's and let the player try 'hacking' (all in-memory, within the simulated universe) youtu.be/-EfWQD7a0mw
github.com hacking game - weekend 2, day 1
YouTube video by T-machine
youtu.be
November 9, 2024 at 5:39 PM
Early build of hacking-game I've been writing for the github.com annual gamejam. Everything is fake! Simulated desktop, servers, telnet client. ... going to add / emulate common basic CVE's and let the player try 'hacking' (all in-memory, within the simulated universe) youtu.be/-EfWQD7a0mw
I quit Twitter almost 10 years ago - although nowhere near as bad as it today, I could already see first-hand the community toxicity - and impact of cynical/grey-hat app design - was making me a worse person just for being active on there. Fingers crossed Bluesky is a breath of fresh air :).
November 8, 2024 at 10:58 AM
I quit Twitter almost 10 years ago - although nowhere near as bad as it today, I could already see first-hand the community toxicity - and impact of cynical/grey-hat app design - was making me a worse person just for being active on there. Fingers crossed Bluesky is a breath of fresh air :).