My only concern is the scale you have selected as we are already close to 100, are you going to have to allow it to be ‘turned up to 11’ at some point?
1,650 karma · joined December 14, 2017
My only concern is the scale you have selected as we are already close to 100, are you going to have to allow it to be ‘turned up to 11’ at some point?
https://blog.scottlogic.com/2025/10/06/delegating-grunt-work...
Using AI Agents to implement UI automation tests - a task that I have always found time-consuming and generally frustrating!
“LLMs don’t know what they don’t know” https://blog.scottlogic.com/2025/03/06/llms-dont-know-what-t...
But I wouldn’t say it is the only problem with this technology! Rather, it is a subtle issue that most users don’t understand
https://randomcompetitions.co.uk/wp-content/uploads/2023/12/...
Absolutely loved that car, used it for hours and hours every week. The best 'toy' I ever had (other than my Amiga A500!).
https://web.archive.org/web/20010405175706/http://fishsoft.c...
I managed to make a decent amount of spending money from that application during my University years.
One interesting lesson I learnt was about enterprise pricing. I think I charged ~$20 for Mosaic Magic, however, I started to get emails from organisations asking about pricing for commercial use. Nothing on my pricing page suggested that commercial use was prohibited, I guess they just thought $20 was rather cheap. From there-on, I charged $150 for "commercial use". Basically, anyone who thought they should be paying more, did!
Finally, Robert Silvers filed a patent and trademark for Photomosaics in ~2000, and was, for a while aggressively pursuing organisations that he felt was infringing. I assume this has all died down now.
I'm also into running visualisation, and created the running report card:
It visualises your year in running, with some fun narrative generated by GPT. Here's my report card:
Agentic AI definitely works for software engineering because we have suitable mitigations for its limitations. It is unclear what those mitigations might be in other fields of application.
https://blog.scottlogic.com/2025/05/08/new-tools-new-flow-th...
https://blog.scottlogic.com/2023/05/04/langchain-mini.html
It is of course quite out of date now as LLMs have native tool use APIs.
However, it proves a similar point to yours, in most applications 99% of the power is within the LLM. The rest is often just simple plumbing.
https://blog.scottlogic.com/2022/02/23/word-embedding-recomm...
Collecting the data helps with recording engine performance, tyre ages, best lap times but is also really useful for recalling how well each setup performed for future reference.
I’m deliberately doing this all in a very low-tech way as my son will be creating a more polished version for a school project. We’re front-running that a bit to give him a good dataset and explore various ideas.
On that note, they do Python in school. For the backend it will be SqlLite and Flask. Any suggestions for the front end tech? This will mostly be forms- and grids-based so nothing sophisticated needed, but some simple client-side logic (e.g. validation, geolocation, simple stop watch) would be good. Ideally this would be python as well. We could use WebAssembly but am wondering if there is a suitable framework that does the is out-of-the-box.
https://github.com/ColinEberhardt/awesome-ai-developer-tools
Categorising these tools is quite challenging!
Totally agree with that.
In fact, I’m much more surprised at just how capable their are of such a wide range of task, given that they have just ‘learnt from the internet’!
The difference is, the hammers and screwdrivers perform a single task, and have been designed and optimised for that specific task.
LLMs are much more versatile and capable of performing a wide range of tasks. Yet, at the same time, their capabilities are ill defined.
Yes, it will generate a middle-of-the-road waffling podcast, but not one with any real depth.
Hard work pays off in the end :-)
https://blog.scottlogic.com/2022/02/23/word-embedding-recomm...
Using embeddings I increased engagement with related articles.
Personally I think embeddings are a powerful tool that are somewhat overlooked. They can be used to navigate between documents (and excerpts) based on similarities - or conversely find unique content.
All without worrying about hallucinations. In other words, they are quite ‘safe’
Been going for 10+ years now. It’s fun to watch my interested (professional and personal) change.
It all started with WPF then Silverlight (RIP), then diversified into HTML5 (when the version number seemed to be a thing). I also had a fun foray into mobile dev for a while, swift / iOS. More recently it’s been quite JS-heavy, and the past year or so, a lot of AI.
There is an underlying theme of open source throughout.
A fun trip down memory lane!