
🧠 Director of Dev | 🎛️ DJ tech | 🏗️ Builder of products, systems & strategy Chasing leverage in automation, markets & ideas. 🤖📈💡 #NZTech #AucklandAI
Auckland, New Zealand
Joined June 2009
- Tweets875
- Following235
- Followers124
- Likes453
Pinned Tweet
Thanks to @steipete for implementing my feature request into Lobster. github.com/openclaw/lobster/…
That’s gonna make my bookmark review and other workflows way snappier. No more handoff lag between cron lobster -> heartbeat -> cron lobster 🦞 ✅
Hopefully don’t have to wait too long before it lands in OpenClaw
176
A larger leadership network is useless if status makes bad news softer. Build a few explicit support relationships where people can challenge you, disclose uncertainty and say what is actually happening.
4
If decisions are final when people leave the room, you’re measuring talk speed, not decision quality. Make decisions provisional overnight, count written objections equally, and keep AI from turning every human interaction into a document.
6
Knowledge work has moved from the 80/20 rule to the 99/1 rule: AI hands you something 99% finished in a minute.
Doing 1% of the work sounds restful. Instead, a March HBR/BCG study coined “AI brain fry”: workers pushed into heavy AI oversight report 33% more decision fatigue and 39% more major errors, with strain surging past 3 concurrent AI tools.
Why? Because the old 80% slog (formatting decks, tidying models) was disguised recovery where your brain worked out the argument.
Delete the cruise, and the whole day is take-offs and landings.
Big day ahead at SIndustries: on Sunday we’re moving Mission Control onto its production cloud infrastructure. A carefully planned migration, a few nervous checks, and a much better foundation for what comes next.
6
An agent can follow the architecture doc, pass every test, and still build the wrong thing when Slack has quietly superseded it. Connectors aren’t context; teams need an explicit system for deciding which source wins.
9
Managers give important work to proven reliable staff because a failed project hurts their own reputation. You should align with that incentive, or create a credible side project when doing AI experiments.
13
An AI initiative that only speeds up one step should be booked as “task improved,” not “workflow redesigned.” Remove no approval gate, leave the same queues and handoffs, and the surrounding work still dominates the cost.
1
23
Coding agents co-wrote 20 million commits on public GitHub last month, up from 3,000 in January 2025, and opened 4.7 million pull requests.
20
Tom Stoffer retweeted
Our economy is growing faster than Australia, the UK, and US. That’s off the back of Kiwi businesses up and down the country.
Last night we celebrated some of them at the Indian NewsLink Business Awards in Manukau.
This election is a choice between a growing economy and No New Taxes with National.
Or more debt, nine new taxes and puting it all at risk with Labour and their mates.
Stick with the plan. Don’t leave the job half done. Party Vote National.
Tom Stoffer retweeted
The year is 2035. AI has taken over the internet. Nothing online is real anymore. Every video, every influencer, every girlfriend, every news story is fake. So everyone logged off.
Digital work was obliterated and automated. The most valualbe skills are now cooking, fixing a truck, farming and fixing things with your hands.
You moved to the land with your wife and 5 close couples.
Farmers and mechanics are the new millionaires. Dinner parties are the new social media. People write letters again. Your kids grow up barefoot, climbing trees and eating steak and eggs instead of scrolling.
News? the only news is your 6th kid on the way.
Turns out AI didn’t destroy humanity. It just made the internet so fake that we finally went back outside.
The cognitive capitalist sees the possibility of an almost limitless expansion of demand, and a world full of minds whose potential has barely begun to be explored.
The best, most comprehensive take on AI I’ve read. After a year of confusion and fear about the future, I finished it feeling like a weight had physically lifted.
It’s long. Make the time.
@vgr is undefeated.
contraptions.venkateshrao.co…
1
2
208
Contest Culture norms turn technical skill into belonging theater: tests, proxies, person-focused excuses.
The counter-signal is strong learning norms, because they make growth more cognitively accessible than defending status. Measure the messages, not the people.
21
Adding people to a late project raises WIP while throughput stays flat, so lead times grow.
Coding is now nearly free, but the sequential parts of SDLC still dominate.
Measure cycle time before chasing AI speedup.
22
This is exactly it! AI, it’s just software bro
1. Oh shit, AI can do my job better than me
2. Software engineering is dead!
3. I can vibe code as much slop as I want!
4. Oh, things are not going well. Fable/Sol/Opus all suuuck
5. But what if I constrain the agent? Put it in a straitjacket?
6. Oh, the results are pretty good now. How do I go deeper?
7. *Orders 12 software engineering books from Amazon*
8. Software engineering is alive!
35
Stop sending every classification to an LLM.
A schema-driven decision model returns probabilities you can drop straight into routing code, and it costs a fraction of the round-trip.
Reserve the LLM for the reasoning the model can't do.
14
If your postmortem ends with "we'll be more careful next time," you have folklore, not a fix.
Ask instead: if the same people left tomorrow, would the failure still happen?
If no, you fixed nothing in the system.
13
Bang on here! Important factory principles
My first software factory was arguably the humble Ralph loop, 14 months ago.
Then I wrote IssueOps, a factory that ran entirely in GitHub Issues and Actions, so I could offload my laptop and keep building while travelling. That cost too much. API billing, amirite?
So I brought the build farm home and Anneal was born. It ran on my Claude subscription locally and wrapped Ralph loops with outer loops, guardrails and tickets. But it lived inside each project, and every copy soon drifted.
About 12 weeks ago I started Holodeck. Instead of putting the factory in the project, I build the projects in the factory. The first project it built was Holodeck itself.
What I've learned:
1. Deterministic gates are the real quality mechanism. The model isn't trusted to judge its own work. Hooks and tests run outside the agent loop. Cheaper models fail and retry instead of committing bad code.
2. The same agent never writes and grades its own work. Test author, implementer and reviewer are separate agents, on different models.
3. Detailed documents first, fast execution after. The spec is now the hard part.
4. Fresh contexts. Always. Tickets keep a log of what was tried and failed so the next loop doesn't make the same mistake.
5. An orchestrator with subagents. The top model coordinates and doesn't do grunt work.
6. Isolation by default. Every agent that edits code gets its own worktree. Runners are throwaway Docker containers with no Docker socket, no source mount and no host ports.
7. Agents get references to secrets, never the values. Enforcement sits in the tooling and hooks, not in the prompt. (I have a product for this coming.)
8. Store a detailed event log. Agents can interact with the API to emulate usage, see real-time logs, and self-improve. Even self-heal.
9. Tools are disposable. Every model release makes some tools redundant, so refactor your stack.
1
29
Didn’t realize South Africa was so high!
Countries by Education Spending (% of GDP)
1. Namibia - 9.1%
2. Algeria - 9.0%
3. Cuba - 8.4%
4. Bolivia - 7.5%
5. Finland - 6.4%
6. South Africa - 6.0%
7. Morocco - 6.0%
8. United Kingdom - 5.9%
9. Brazil - 5.6%
10. United States - 5.4%
11. South Korea - 5.4%
12. France - 5.3%
13. Colombia - 5.3%
14. Germany - 5.2%
15. New Zealand - 5.2%
16. Australia - 5.1%
17. Argentina - 5.0%
18. Kazakhstan - 4.9%
19. Chile - 4.9%
20. Canada - 4.8%
21. Uruguay - 4.8%
22. Spain - 4.6%
23. Saudi Arabia - 4.5%
24. Peru - 4.4%
25. Poland - 4.3%
26. Russia - 4.2%
27. India - 4.1%
28. Italy - 4.1%
29. Mexico - 4.1%
30. Philippines - 4.0%
31. Kenya - 4.0%
32. China - 3.9%
33. Malaysia - 3.5%
34. Japan - 3.3%
35. Vietnam - 2.9%
36. Iran - 2.8%
37. Thailand - 2.5%
38. Indonesia - 1.3%
39. Nigeria - 0.3%
Source: World Bank, UNESCO Institute for Statistics (UIS), and national government data.
1
24
A URL fetcher can validate a public IP, then resolve the same hostname again during the request and land on a private address.
I fixed that DNS-rebinding gap by resolving once and pinning the validated IP into the connection.
24













