tag:blogger.com,1999:blog-78745552932439798332026-01-23T00:59:10.228-08:00Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.comBlogger17125tag:blogger.com,1999:blog-7874555293243979833.post-77806357516609323782025-12-07T04:32:00.000-08:002025-12-09T06:46:33.935-08:00

“A little over a year ago, we copied and pasted AI code snippets.  Today, we have spec-driven development.  Yet the biggest lesson isn’t about the tools - it’s about how we use them.”We’ve come remarkably far in twelve months.  From basic code completion to sophisticated integrated assistants.  From vibe coding to specification-driven development.  The technology has

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-3041520439186047832025-11-10T14:36:00.000-08:002025-11-10T14:38:41.434-08:00

“Ask ChatGPT to write C code and it’ll give you Python with semicolons.” AI coding tools have a dirty secret: they’re brilliant at some programming languages and barely competent at others. The difference isn’t random - it’s a direct result of what they were trained on. And what they were trained on is overwhelmingly JavaScript and Python.TL;DR: AI coding quality varies dramatically by language.

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-90924720402713953312025-11-03T07:58:00.000-08:002025-11-03T08:16:35.787-08:00

I watched a team switch AI coding tools mid-project.  Three weeks later, their database architecture had quietly changed and half their API endpoints had lost authentication.Switching AI coding assistants mid-project isn’t just inefficient.  It’s dangerous.TL;DR: Switching AI coding tools mid-project silently breaks your architecture, creates security vulnerabilities and introduces

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-37445974872968341302025-10-24T04:03:00.000-07:002025-11-03T08:12:55.255-08:00

First-generation AI coders let you chat your way to code. Second-generation tools are discovering that coffee-shop conversations don’t build production systems.Eighteen months ago, Cursor and Cline pioneered AI-assisted coding. You described what you wanted, the AI generated code and if you were lucky, it mostly worked. We called it “vibe coding” - casual, conversational and utterly inadequate

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-1155196393297248382025-10-24T02:52:00.000-07:002025-10-24T03:13:11.965-07:00

Six months ago, everyone said AI would replace developers.  Today, most AI-generated code needs more debugging than writing from scratch.The AI coding revolution was supposed to be here by now.  GitHub Copilot would write our applications.  ChatGPT would eliminate junior developers.  Cursor would make senior developers 10x more productive.Instead... we’re drowning in

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-39282367738163233542025-09-09T14:59:00.000-07:002025-10-01T15:58:32.901-07:00

AI vendors are racing to offer million-token context windows.  But... they're not doing it for your benefit. Remember when 4K context windows felt limiting?  Then 8K arrived.  Then 32K.  Now we're being sold 128K, 200K and even million-token windows as the solution to all our AI problems.  Sadly, it's all a con. Here's what they're not telling you. How AI Conversations

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0Reading, UK51.455120099999988 -0.978747523.144886263821142 -36.1349975 79.765353936178826 34.1775025tag:blogger.com,1999:blog-7874555293243979833.post-53192896503996308362025-05-27T01:24:00.000-07:002025-05-27T01:24:51.453-07:00

I have been most honoured to be featured in the GCS Leaders Podcast series.  David Bloxham and I have a fun and meandering conversation about the myths and realities of AI, where it is today and how to safely use AI to your advantage.See all of the GCS Leaders Podcast series, right here (https://www.youtube.com/watch?v=PxFJX7RFXzI), GCS is a really innovative and leading the

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-66923366625247412822025-04-16T07:31:00.000-07:002025-04-22T05:31:00.816-07:00

The recent viral fad to create cute, self styled action figure pictures of yourself or a favourite pet is not the best use of AI ever imagined.  Each image uses lots of GPU time and that means lots of energy.  An article on Techradar raises concerns about this massive misuse of AI fueled by this FOMO trend.  Even Sam Altman likes the idea, but he says it's melting the OpenAI

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-65594571823127201652025-03-31T06:56:00.000-07:002025-04-22T03:22:25.545-07:00

Over the past month ro so we have seen a growing number of articles about AI market over hype and in particular, Microsoft which has pulled back from plans to build new data centres and also from letters of intent relating to purchase of 2 Gigawatts (GW) of energy, representing a significant scaling back.  The general feeling would appear to be that AI's energy consumption is already too

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-7396642949460883982025-02-26T03:03:00.000-08:002025-04-16T06:51:11.394-07:00

The EU AI Act is the world’s first comprehensive law governing AI, setting a precedent for how organizations across industries must handle AI responsibly.  Among its many provisions, a crucial but often overlooked requirement is AI literacy—a mandate that ensures employees working with AI have the necessary skills and understanding to assess AI risks and opportunities effectively.From

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-74356125235127805472025-02-25T02:51:00.000-08:002025-04-16T06:52:47.794-07:00

In today's fast-paced business landscape, AI adoption is emerging as a transformative strategy that mirrors the revolutionary approaches of the past. Much like the 1990s Business Process Re-engineering (BPR) and the 2000s Kanban and Lean methodologies, integrating AI into your operations is about optimizing processes, enhancing decision-making and securing a competitive edge.  However, the

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-66503914892386839982025-02-12T05:13:00.000-08:002025-04-16T06:56:18.128-07:00

The AI industry found itself at another potential inflection point with Elon Musk's expressed interest in acquiring OpenAI, the company he co-founded in 2015 before departing in 2018.  This development is particularly noteworthy given the complex history between Musk and OpenAI, as well as the current state of the AI industry. Musk's initial involvement with OpenAI was rooted in promoting

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-14301516196744512532025-02-06T05:23:00.000-08:002025-04-16T06:55:54.414-07:00

DeepSeek has made waves by delivering high-performing AI models with significantly lower resource requirements than industry giants like OpenAI and Anthropic.  Here's how they've done it:Resource Efficiency at Its BestInnovative Architecture: Using a mixture-of-experts (MoE) and FP8 precision, DeepSeek optimizes hardware use, making training more efficientData Optimization: Focusing on data

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-73121043309546136912025-02-05T05:27:00.004-08:002025-02-05T05:29:05.449-08:00

In today's fast-paced digital landscape, AI isn't just a tool for generating content - it can also help you fine-tune your prompts themselves for better results.  By using AI to analyze and refine your queries, you will recieve clearer, more creative and targeted responses.  If you're counting tokens, it will also save on usage costs.So try asking your AI system of choice:"Please

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-85495708298801881632025-01-27T08:19:00.000-08:002025-01-31T02:39:46.950-08:00

Tools like Ollama and llama.cpp run models locally, offering users unprecedented control and privacy over AI operations. However, this control comes with its own set of security considerations.  This blog post delves into the potential security threats and provides insights into how to manage these risks effectively, especially with questions over the provenence of models like DeepSeek

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-79762784078733972582025-01-13T04:05:00.000-08:002025-01-28T06:33:16.609-08:00

Since I first started using ChatGPT, my prompts have always been courteous "Please can you..." and "Thank you" at the end of the conversation.  A friend commented the other day that this makes no difference whatsoever to the LLM and is really just wearing out my keyboard prematurely.I take a different view... Just like humans don't take kindly to having orders barked at them, I think AI will

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0tag:blogger.com,1999:blog-7874555293243979833.post-36076913247994431402025-01-06T01:00:00.000-08:002025-01-28T06:32:54.656-08:00

Hi, and welcome to the renewed Lanboss!  Our previous clients will remember us for our networked systems monitoring, management and security tooling... In renewing Lanboss, we're using our data science and anaylsis backgrounds to help organisations prepare datasets for LLM training and fine-tuning, alongside our user education and governance services - all to promote the safe use of AI

Lanboss.aihttp://www.blogger.com/profile/08131872598457752886noreply@blogger.com0