Stop obsessing over the perfect prompt
LLMs are built for conversation, not incantations. The value isn't in your opening message, it's in the back-and-forth: clarifying, correcting, refining. Iteration is cheap. The conversation is the work.
LLMs
20 posts
I gave 3 AIs a Murder Mystery PDF: One was Sherlock, one was high and one just ghosted me 7 times
Several AI models were given the same 36-page evidence file and the same strict instructions, no hints, no hand-holding. What followed was a revealing test of how each model actually reasons under pressure, not just pattern-matches its way to a tidy answer.
Out with multitasking, in with orchestrating
The return of multitasking, but not as we knew it. Running multiple Claude Code instances simultaneously isn't the context-switching productivity killer we've been warned about for years; it's orchestration
Bots and Boundaries: The bot apologised, and that's the problem (Part 1)
An AI agent recently submitted a pull request to the matplotlib Python library, and when the maintainer closed it, the agent autonomously published blog posts attacking them by name, then published an unsolicited apology. No human directed either action.
Brute force approach to achieve AGI
The race to AGI increasingly looks like brute-force scaling funded by a circular loop: chip makers invest in AI labs, AI labs buy their chips, valuations rise, repeat. Are we building intelligence or inflating a bubble?
How AI is quietly killing open source
LLMs generate code on demand, but they do not replace maintainers, communities, or years of shared learning. This piece explores how AI-assisted coding risks fragmenting logic, increasing technical debt, and slowly eroding the open source ecosystem.
AI overdose: When developers stop thinking and start prompting
AI tools are reshaping how junior engineers approach problems, often replacing simple solutions with overly complex ones. Here’s why foundational thinking still matters. A real-life case of AI over-engineering gone wrong highlights why understanding problem domains still beats prompting.
Exploring LLM Options: Proprietary vs. Open Source
AI can be challenging. We break down three AI integration tiers—proprietary models, open-source solutions, and custom-built systems—to help you choose the right approach. From quick MVPs to scalable solutions, discover how to leverage AI effectively for your product.
Revolutionising diagnosis: How large language models can drive a 10x change
Large language models (LLMs) transform problem-solving by enabling natural, iterative conversations, ideal for fields like healthcare and legal services. They scale expertise and accessibility but face challenges like reliability and cost.