Furó Tamás-Márk
furotmark.github.io - ok, I finally had time and set up the @standard.site for my blog. @sequoia.pub cli helped a lot
Metacognitive awareness in the era of AI
OMG, the Start and Search in Windows is actually usable!
Furó Tamás-Márk reposted
By replacing manual issue verification with isolated AI subagents running in GitHub Actions, the Astro maintainers reduced open issue count by 85%. This post explores the architecture behind automated bug reproduction, patch verification, and preview releases. https://cfl.re/4wFuCKs
Really good video from @burkeholland.bsky.social explaining how ai input caching works
The cost of writing code dropped; the cost of owning it didn’t. A framework for deciding which changes are actually cheap in the AI era.
I must say after a day of use these models are good, but boy they are a lot faster than other models
GPT-5.6 comes in three model tiers. → Sol handles long-horizon coding and agentic work that demands planning, tool use, and follow-through. → Terra balances performance and cost for everyday work. → Luna brings speed to well-defined, high-volume work. (1/2)
Furó Tamás-Márk reposted
It would be great if we could see if the model has changed or has updates when using @github.com copilot. I don't know why but it seems that the behavior changes on these models. For similar runs, I had better results with GPT last weeks, now their result are bad, but Claude's are much better.
So weird hearing @gergely.pragmaticengineer.com in his native tongue (Hungarian) Still a really good interview!
Furó Tamás-Márk reposted
Great site to have an answer for everything related to software engineering
I really like these interactive visual essays This explains what happens when you send a message to Claude Code ->
[Blogged] A while ago, I built a custom Cosmos DB memory layer for Azure AI Agents. Sharing how I did it:
Did I Mention You Have No Excuse for Skipping Regression Tests Anymore
Good to see Thomas Bangalter active again!
Furó Tamás-Márk reposted
If you use GitHub (especially if you pay for it!!) consider doing this *immediately* Settings -> Privacy -> Disallow GitHub to train their models on your code. GitHub opted *everyone* into training. No matter if you pay for the service (like I do). WTH github.com/settings/cop...