#Tag · Bonfire Dinteg Labs

#AMLD Agent-Mediated #LiterateDevelopment methodology first draft, ready to be tested.
I would love some feedback.
https://hg.sr.ht/~travisfw/amld-method
#agenticCoding

~travisfw/amld-method - Agent-Mediated Literate Development methodology applies Literate Programming to agentic coding, aiming to reap the benefits of delegation to an agent in a stable, maintainable code base, where documentation is code. - sourcehut hg

Travis F W

@travisfw@fosstodon.org replied · 2 days ago

#Claude likes #AMLD

🙶The methodology aligns well with how I work in several respects:

- Plan-first, human-affirms (wip.adoc review step) matches the principle of checking before acting
- Structured logging (amld/log/, handoff files) compensates well for my lack of persistent memory across sessions
- Declarative design docs as the source of truth is sound — code should reference design, not the other way around
- Ticket discipline gives me clear scope boundaries, reducing drift

Michał "rysiek" Woźniak · 🇺🇦

@rysiek@mstdn.social · 7 days ago

Claude Desktop app was unresponsive for users for several hours because it did not account for daylight savings time:
https://status.claude.com/incidents/pqpgkf52p3tg

> Root cause: Users with scheduled tasks in Claude Cowork or Claude Code who are in a timezone that observed daylight saving time last night were affected by an infinite loop. When the app tried to locate tasks scheduled during the “skipped” hour, it couldn’t resolve them and got stuck.

Enterprise quality. Serious company. Many wow. 🤡

#AI #Hype #Claude

Chad :mstdn: boosted

knoppix

@knoppix95@mastodon.social · last week

Claude Opus 4.6 AI found 22 Firefox vulnerabilities (14 high-severity) in two weeks, helping patch Firefox 148 — nearly 20% of 2025's high-risk bugs. 🧩

Anthropic notes AI excels at bug hunting but struggles with full exploits, marking a shift where AI-assisted analysis joins fuzzing as a key security tool. 🛡️

🔗 https://thehackernews.com/2026/03/anthropic-finds-22-firefox.html

#TechNews #Privacy #Firefox #AI #Security #Anthropic #Claude #Cybersecurity #Vulnerabilities #Mozilla #Browser #OpenSource #Hacking #DevSecOps #FOSS #Opus

The Hacker News

Anthropic Finds 22 Firefox Vulnerabilities Using Claude Opus 4.6 AI Model

Anthropic’s Claude Opus 4.6 AI found 22 Firefox vulnerabilities, including 14 high severity, helping Mozilla patch flaws in Firefox 148.