Advertisement Β· 728 Γ— 90

Posts by Mark Farragher

(2/2) It then tried to hack into my browser session to steal my login token. I was watching in real time and managed to pull the plug in time.

Did I mention you should never run an AI agent unattended?

1 week ago 1 0 0 0

(1/2) Yesterday I was building a web app with OpenCode, GitHub Copilot and Deno. A web page didn't look right, and I asked Copilot to check it out and tell me what's wrong.

The agent loaded the page, got an access denied error, and decided that it needed admin privileges to debug this properly.

1 week ago 0 0 1 0

I'm a fan of your work and your posts, by the way! Please do not take this as personal criticism.

2 weeks ago 0 0 0 0

Yeah ok, good point. But I'm getting tired seeing yet another AI chatbot. A bot is the least creative thing you can build with this tech and I'd like to see more useful applications. I very much enjoyed seeing your memory tool coded in Swift. GenAI is great for exploring new programming languages.

2 weeks ago 0 0 1 0

I'm not comfortable seeing this utterly frivolous use of AI. Given AI's huge energy requirements, copyright issues and societal upheaval, a talk-like-a-victorian chatbot tech demo maybe isn't what we should focus on right now. I was much more impressed by your AI-coded menu bar widget for macOS.

2 weeks ago 0 0 1 0
Post image

The future is here

2 weeks ago 45 11 1 0
Infographic with a gauge at 42% and text: S&P Global Market Intelligence 2025. 42% of companies abandon their AI initiatives.  AI FIXER will make sure you are in the other 58%!

Infographic with a gauge at 42% and text: S&P Global Market Intelligence 2025. 42% of companies abandon their AI initiatives. AI FIXER will make sure you are in the other 58%!

#AIFIXER www.aifixer.nl

3 weeks ago 0 0 0 0
Advertisement

(2/2)
In a sane world, we would have static type systems, code contracts, static analyzers, compilers and proof checkers in our toolchain and #codeslop wouldn't stand a chance.

It's time for the industry to finally grow up.

3 weeks ago 0 0 0 0

(1/2) The real problem with #genAI is that the software industry has operated for decades with no regard for quality at all.

Today #AI coding agents produce low quality code at scale. And some developers are fine with running these tools day and night with no human oversight.

3 weeks ago 2 0 1 0
Preview
EspoCRM: Open Source Alternative to HubSpot, Salesforce and Pipedrive Open-source CRM software for managing customers, companies, projects and opportunities. Intuitive interface with cloud and self-hosted options available.

EspoCRM β€” Complete customer relationship management made simple

⭐ Stars: 2,830
πŸ”— Forks: 809
⏩ Last commit: Mar 15, 2026
βŒ› First commit: Sep 25, 2014

4 weeks ago 4 1 0 0
Post image

Algebraic creatures Made with #Python #NumPy #Matplotlib and
@marimo.io

4 weeks ago 41 8 2 0

(3/3) My generated code must run in a compiled language, with strong type checking, and within a security sandbox. This is why I stay away from #NodeJS and embrace #Deno instead.

4 weeks ago 3 0 0 0

(2/3) I create highly modular app architectures and try to implement each module with off-the-shelf #opensource components. I only use generated code to fill in the gaps, and I strictly separate code and design so that I can easily refactor the design later if needed.

4 weeks ago 2 0 0 0

(1/3) After a busy week of #agentic #AI #coding, I've come up with the following strategy:

I treat my coding #agent as junior programmers. I run a tight loop where I prompt, and immediately check its work afterwards and refactor if I don't agree with the code. I never let agents run unattended.

4 weeks ago 2 0 1 0

Yes, that's true! Plus, these tools are all well designed. OpenCode is fast and very frugal with tokens, Gemini's "thinking" threads are usually short, and GH Copilot charges per request instead of per token. I get much more work done for the same budget.

4 weeks ago 1 1 0 0

During the migration from #OpenAI to #Anthropic, I'm going against the grain by migrating from Anthropic to #GitHub #Copilot Pro πŸ€ͺ

I'm building an app with #OpenCode, Copilot and #Gemini Pro 3, and it works great. Gemini is great with #typescript and #bootstrap. This is my default agent stack now.

1 month ago 3 0 1 0
Infographic with text: "95% of Generative AI pilot projects fail to deliver a measurable impact on the P&L". Attributed to the MIT NANDA Report, 2025. The card links to the AI FIXER website at https://www.aifixer.nl. Phone: 06 44 768 758. Email: hello@aifixer.nl

Infographic with text: "95% of Generative AI pilot projects fail to deliver a measurable impact on the P&L". Attributed to the MIT NANDA Report, 2025. The card links to the AI FIXER website at https://www.aifixer.nl. Phone: 06 44 768 758. Email: hello@aifixer.nl

According to the MIT NANDA Report of 2025, 95% of generative AI pilot projects fail to deliver a measurable impact on the P&L.

AI FIXER puts you in the 5% that succeeds!

1 month ago 0 0 0 0
Advertisement
Post image

I'm very excited to announce AI FIXER, a new collaboration between Composition8 | Training & Business Consulting and me.

π’π²π¬π­πžπ¦π¬ 𝐈𝐧𝐬𝐩𝐒𝐫𝐞𝐝 π€πˆ: we help you design AI that makes sense.

More at AIFIXER dot NL: www.aifixer.nl

#aifixer

1 month ago 1 0 0 0
Preview
On Swarms, Davos and the Power of the Powerless Let’s take a look today at the power of individuals against world leaders and what swarm improvisation principles suggest is best to do. This is a rather unusual post for this blog, but hey, …

Just read this great piece by Thomas Johannsen, a perfect resource for exiting the problematic big tech monopolies (and inspiring you to do so). If you've already made the shift to Bluesky for ethical reasons, here are the next steps in your journey toward digital sainthood.

2 months ago 208 45 21 8

We are about to go from micro services running on the cloud to monoliths running on the desktop.

2 months ago 203 19 17 13

Typical vibe-coded shit. I was messing around with Moltbook only 10 minutes ago and noticed that several API endpoints do not check for the bearer token at all.

2 months ago 1 0 0 0
The Superior Statements Of Orac | Blakes 7
The Superior Statements Of Orac | Blakes 7 YouTube video by Spaced Out

orac
www.youtube.com/watch?v=XCg4...

2 months ago 1 1 1 0
Post image
3 months ago 24 2 0 0
European Commission - Have your say European Commission - Have your say

I responded to the @ec.europa.eu public consultation on an #European Open Digital Ecosystem. This is my proposal for an #EU #OpenSource policy:

ec.europa.eu/info/law/bet...

3 months ago 2 0 0 0
Post image
4 months ago 12 4 0 0
Advertisement
Preview
GitHub - pgvector/pgvector: Open-source vector similarity search for Postgres Open-source vector similarity search for Postgres. Contribute to pgvector/pgvector development by creating an account on GitHub.

Don't forget pgvector: github.com/pgvector/pgv...

3 months ago 0 0 1 0
Preview
The Enshittifinancial Crisis Soundtrack: Lynyrd Skynyrd β€” Free Bird This piece is over 19,000 words, and took me a great deal of writing and research. If you liked it, please subscribe to my premium newsletter. It’s $70 a year, ...

My final newsletter of 2025: We're in The Enshittifinancial Crisis, the fourth stage of enshittification, where companies turn on their shareholders. Unprofitable, unsustainable AI threatens future of venture capital, private equity and the markets themselves.
www.wheresyoured.at/the-enshitti...

3 months ago 1888 469 58 91
Preview
GitHub - saikiranrallabandi/inframind: InfraMind: Fine-tuning toolkit for training SLMs on Infrastructure-as-Code using GRPO/DAPO. Achieves 97.3% accuracy on IaC generation. InfraMind: Fine-tuning toolkit for training SLMs on Infrastructure-as-Code using GRPO/DAPO. Achieves 97.3% accuracy on IaC generation. - GitHub - saikiranrallabandi/inframind: InfraMind: Fine-tun...

github.com/saikiranrall...

3 months ago 0 1 0 0
The device you've been waiting for!
The device you've been waiting for! YouTube video by andy kirby

meshcore device www.youtube.com/watch?v=z6IO...

3 months ago 2 2 0 0