I've been automating payroll for my company using Claude, but one thing continually got in the way:
going from Xero to Airwallex to upload batch transfers so that I don't have to input each employee 1 by 1.
Xero outputs a CSV file for this purpose, but Airwallex expects a special Excel template to be used.
So I built a CLI that you can use locally or give to your agent: https://t.co/vZhrLtbjqr
Instantly converts from Xero to Airwallex batch payment file formats.
Thank me later.
One thing I love about Hermes Agent, I only had to ask it to send me a daily email with the best flights to Bali - it also takes into account how agonising the flight will be by layovers, duration, airline etc.
Jetstar is scaled up here because it’s the most direct option.
This is it.
Everything learned spending millions on longevity.
From: Your Immortal Unc and Auntie.
To: Our Immortal nieces and nephews.
0. Sleep is the world's most powerful drug.
1. Be in your bed for 8 hours
2. Same bedtime every night, any time before midnight
3. Don’t eat right before bed
4. Calm foods for dinner
5. No screens 1 hour before bed
6. Avoid added sugar (be aware it’s in everything)
7. Avoid all things in an American convenience store
8. Avoid fried foods
9. Shoes off at the door
10. Eat whole foods, particularly veggies fruits nuts legumes berries
11. Walk a little after meals or air squats
12. Get your heart rate high routinely
13. Lift heavy things
14. Stretch daily
15. Water pik, floss, brush, tongue scrape, morning and night
16. Make an effort to drink water
17. Get sunlight when you wake up (UV is low)
18. Protect skin in midday sun
19. Stand up straight
20. See at least one friend once a week
21. Avoid plastic where you can (in all things)
22. Circulate air in rooms
23. When stressed, breathe, learn to calm your body
24. Go to the dentist
25. Avoid sitting for long times
26. Protect your hearing, the world is too loud
27. Alcohol is bad for you
28. Finish coffee before noon
29. Avoid bright lights after sunset
30. If obese, look into a GLP
31. Sleep in a cold room
32. Texting while driving is dangerous
33. Turn off all notifications
34. Limit social media use
35. Don’t smoke anything
36. If you struggle to sleep, read a physical book before bed
37. 1 hour before bed have a calm wind down routine: bath, read, light walk, listen to music
38. The body is a clock and loves routine. Have a daily morning and evening schedule.
39. Avoid long distance travel where you can
40. Baby steps first: incorporate new things slowly
41. Do less… most things don’t work.
Bonus points if you get your blood checked.
Start here, it will change your life.
@jdrhyne@nutrientdocs Is your benchmark dataset public? I'd like to try it on the tools we're using internally to see if we should switch to your product.
Cornell study just dropped a nuke on corporate jargon lovers:
People who get inspired by “synergizing paradigms” and “growth-hacking synergistic leadership” are worse at actual decision-making, lower in analytic thinking, and help promote the worst bosses.
Corporate BS isn't a skill—it's a red flag.
Bonus: they’re also happiest at their jobs 😭
Link: https://t.co/1CsQgZ2uXT
Who's the biggest paradigm-synergizer in your office? 👀
On a flight to Tokyo with barely functional wifi. Too slow for Claude/Amp, didn't pack a big enough local model to be productive.
Solution: spun up a GCP VM in Sydney, connected via mosh (https://t.co/8O11bzZseG) which handles insane latency and packet loss. Now I can run multiple Amp instances over SSH, close my laptop, change connections, check back later. Everything just keeps running.
Additional level up: run this in tmux and ask amp to create some friendly aliases for you to remember.
ps: Don't forget to security harden your VM. The mikr13/secure-server-setup-skills skill is a valid choice here.
The space moves fast for sure. What sold me on Amp is the multi-model approach (Opus 4.6 + GPT-5.2 oracle), subagent parallelism, and the Librarian for cross-repo research. One thing people miss is Threads. Every session is saved, so you can ask the agent to read what it did previously in any part of your codebase, not just the current folder. Great for picking up where you left off.
@miaugladiator1@AmpCode 100%. Being able to say "use one subagent per file" and have them work in parallel with their own context windows is wild. And the oracle for second-opinion reasoning on hard bugs – chef's kiss.
It uses multiple models actually: Opus 4.6 as the main agent, GPT-5.2 as an oracle for complex reasoning, plus fast models for lighter tasks. The orchestration layer (subagents, oracle, librarian, permission system) is what makes the difference. Calling it a wrapper undersells it.
Multi-model — it uses Opus 4.6 as the main agent but can call a GPT-5.2 "oracle" for hard reasoning tasks. It spawns subagents for parallel work (e.g. "convert these 5 files to Tailwind, one subagent per file"). Has a Librarian that can search remote GitHub repos, and reads https://t.co/ZfZ0kVQlUK files for project conventions. It's an agent harness, not a chat wrapper.
@arnestrickmann@AmpCode That's a great breakdown. My experience has been similar, Amp just "gets" the codebase context better. It reads https://t.co/dJtPwv2apb files, follows conventions, and chains subagents together to ship entire features autonomously. The "smart" label is accurate.
Software is eating the world, and AI is eating software.
2026 will be the year companies realise they can vibe-code most services they pay >$50k/year for, and do it for <$5,000 in time and tokens.