Dagens Vibes — 5. oktober 2026

Fra X-feedet

2.500 PR’er er ikke pointen. Verifikationen er.

Lauren Tan deler sin talk om 2.500 PR’er på en måned. Den brugbare pointe: lad agenterne afprøve deres arbejde, og gør gentagne fejl til håndhævede regler.

lauren@poteto

if you're wondering how we ship thousands of PRs, check out this talk! and then watch https://t.co/U7e4nfhZ1W for the extended Q&A with the one and only @mattpocockuk

@poteto

here's how i shipped 2,500 PRs last month to production this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly https://t.co/NgrGz7tmPM

♥ 715 · ↻ 40 · 💬 42 · 🔖 634

https://x.com/poteto/status/2106893179605876927

Cloudflare gør hele platformen til agentværktøj

Miessler har flyttet sit workflow til cf: over 3.000 Cloudflare-operationer, JSON som standard og typet konfiguration. Mere interessant end endnu et MCP-wrapperlag.

ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ 🛡️@DanielMiessler

Welp, I'm fully migrated from wrangler to cf. Briliant work by the @Cloudflare team on this. This is a perfect example of not only having awesome products, but also having them be fully agent-accessible. https://t.co/isgXF94YaS

♥ 201 · ↻ 17 · 💬 6 · 🔖 129

https://x.com/DanielMiessler/status/2106818118668718564

Model-vibe check: Opus arbejder; Astra krydsforhører

Daniel San oplever et markant løft i Opus 5.5’s browserarbejde. Robin Ebers bruger Astra som kritisk planreviewer — med overengineering som prisen, og Opus som hverdagsvalg.

Daniel San@dani_avila7

Huge improvement in Claude’s Chrome extension browser use I left it running for 72 minutes on a classification task. It executed 1,000+ actions and used 356K tokens with Opus 5.5 I tried it a few months ago and stopped using it because it was slow, often got lost navigating the interface, and failed to complete longer tasks The improvement is massive! 👏 Leaving the link here if you want to download it and try it: https://t.co/vN8eh9IYAR

♥ 47 · ↻ 3 · 💬 8 · 🔖 21

https://x.com/dani_avila7/status/2106833194477588903

Robin Ebers@robinebers

serious hot take: astra > opus hear me out before you start crying in my comments i'd never pick astra over opus for daily work, but every time i run an adversarial review on a plan that opus created, astra absolutely tears it apart 30% of astra's feedback is over-engineering, yes but the other 70% are genuine holes and improvements that, honestly, opus should have paid attention to TL;DR: - astra still is significantly smarter/more diligent - despite this, opus is the better everyday model once OpenAI gets speed and cost under control, i'd place bets that they will have the better overall model (for the first time ever, i'd argue)

♥ 237 · ↻ 3 · 💬 87 · 🔖 56

https://x.com/robinebers/status/2106667582149239193

Forgren en Claude-session, ikke bare dens kode

Time Machine optager prompts, værktøjskald og edits og lader dig genstarte fra et tidligere punkt i en separat worktree. Samtale og kode følger med; originalen bliver stående. Endelig en tidsmaskine med et nogenlunde afgrænset blast radius.

Daniel San@dani_avila7

Introducing Time Machine for Claude Code Works in both Claude Desktop and Claude Code CLI /timemachine records your session as a timeline, including prompts, tool calls, edits, Bash commands, and turn endings Pick any point and fork from there, It restores both the conversation and the code state from that moment into a separate Git worktree and branch, while your original session stays untouched Install: npx claude-code-templates@latest --mod productivity/session-time-machine Then run: /reload-plugin /timemachine

♥ 90 · ↻ 5 · 💬 12 · 🔖 83

https://x.com/dani_avila7/status/2106910092620689432

/retro retter agentens arbejdsmiljø

Matt Pococks skills v1.3 gør retrospektivet konkret: find friktion i tidligere sessioner og forbedr navigation, checks og steering frem for bare at bede modellen tage sig sammen. Versionsskiftet omdøber også CONTEXT.md til GLOSSARY.md.

Matt Pocock@mattpocockuk

Prompt of the day: 1. Re-check mattpocock/skills for the v1.3 release. Rename CONTEXT.md to GLOSSARY.md. Check /setup-matt-pocock-skills for any required changes. Perform a diff of the skills in my repository vs Matt's. 2. Get a sense for how I use Matt's skills: scan my last 25 sessions for skill invocations. Then, recommend how this release might improve my workflow. Enjoy v1.3, pals.

♥ 2.054 · ↻ 51 · 💬 50 · 🔖 2.321

https://x.com/mattpocockuk/status/2106730768789602313

Nyhedsbonus

Googles open source-bug bounty drukner i AI-rapporter

Googles OSS-belønningsprogram er sat på pause: langt de fleste automatiske indsendelser er ugyldige, skriver TechCrunch søndag. Billigt at generere, dyrt at efterprøve.