We should probably do something about this. š¤
2026-07-30 18:31:44
The book doesnāt seem to have much reference to AI, but Catās (@grimalkina) āBrains in jarsā model of software teams seems to describe exactly what LLMs might be (are?) good at replacing.
āInteractions, social learning, and shared problem solving are invisible in this modelā – and seem to disappear when agentic coding takes over.
2026-07-30 18:06:14
āgood psychology is _how_ good software work happens.ā
š
Reading @grimalkinaās āThe Psychology of Software Teamsā (because Iām VERY interested in the people side of software development)
It looked like quite a dense, academic book. But itās actually short, punchy, and very well written (so far!)
2026-07-28 17:52:25
Today was one of those āGlad I know lots of weird stuff about computers that not a lot of people knowā days.
Enjoying doing deep work with the deep knowledge. š
2026-07-27 08:54:42
Oh gah! UK Plug-in Solar will be legal from 27th August but does NOT include kits with batteries. Itās panel+inverter only.
2026-07-26 10:04:39
I spent some of yesterday watching the Patreon guy talk passionately about taking risks, putting it on the line, and doing whatās hard.
https://youtu.be/17_HcR95YBc?t=3390
Today I read that heās laying off 20% of his workers.
https://www.theverge.com/tech/970211/patreon-layoffs-ai
And now Iām very confused about this guy.
2026-07-26 09:15:50
Finally watched Ready Player One last night. Iāve not read the book.
Was disappointed that it just seemed to be a blockbuster CGI fighty thing.
Is the book a more interesting story?
2026-07-25 15:03:15
Thinking about this⦠it if I have included an open source license then they are allowed to create a derivative work.
And they are supposed to keep a copyright notice, so I must be giving consent for that personally identifying information to be used.
So this seems like a legitimate thing to do with open source code, doesnāt it?
Regardless: this stinks – not least because they have included code of mine that has no license and thus is NOT open source. š”
2026-07-23 22:49:11
First full day of school holidays.
Took kids to the local high ropes place.
Very fun. But Iām surprised this slack line fix got past health and safety! š¬
2026-07-23 22:20:36
We finally finished this epic name-grouping quiz today! Only took us 7 months and 1509 mistakes. we really werenāt very good. But I can close the tab now! Yay!!!
2026-07-21 21:45:45
Iām sorry, what now???
āEvery time an EV connects to a charger, it establishes an IP network over Power Line Communication (PLC).ā
A mini network between your car and charger! Fun!!
āThis network was designed for V2G protocols. But we also discovered other EV charger operating system services listening on these network interfaces.ā
š«£
https://www.saiflow.com/blog/the-hidden-ccs2-attack-surface-on-ev-chargers
2026-07-20 22:31:10
I do wish @calebporzio was properly on these socials. The journey of self-discovery he went on in his last two podcasts was epic. I like where he landed. He is not Ian. He works differently. He finds joy in different things. That is a good thing. Stop trying to be someone you are not!
2026-07-20 22:07:08
I hate to do this, but this is a test!!
2026-07-19 12:56:12
I am a member of my local Makerspace. I have access to a laser cutter.
I need to practice my new skills!!
2026-07-19 10:44:21
I hear that this new movie āThe Odysseyā is based on a book.
Do you think I should read the book before seeing it at the cinema?
š¤
2026-07-18 11:50:12
I find myself wondering if there is a job in optimising LLM agent skills by converting them to run deterministically with real programming/scripting languages.
I see so much āifā¦thenā, decision trees, and even literal āfor eachā mechanics in instructions to LLMs.
This week I reduced a part of a skill that took 14s to run with an LLM to a PHP script that took 2 seconds (mostly querying an API) and used zero tokens.
With companies asking people to reduce token use, this seems like a no-brainer.
2026-07-18 11:45:21
@samir I just took time to properly read https://functional.computer/blog/llms-cant-program
Itās very good. Thanks for writing up your experiences.
Iām intrigued that you are having/have had success with getting LLMs to fill in the gaps or identify weaknesses.
In my experience LLMs are very good at summarising code – they work well when they have all the information they need to respond.
Iāve found them very hit and miss when asking them to be inventive. Sometimes they are amazing, but itās unreliable.
2026-07-16 22:34:42
I am particularly proud of the TikTok-worthy, white-man-bakes-sourdough / ASMR crossover video! š
2026-07-16 22:30:48
The people asked (well, some friends over on Bluesky did!), and the people have now received.
After sharing a photo of my sourdough loaf this morning, I was encouraged to write up my process/recipe.
So here is my almost-jargon-free, real-life sourdough guide!
https://rosswintle.uk/2026/07/a-real-life-jargon-free-sourdough-bread-process/
2026-07-16 08:49:14
Baking mornings are the best kind!