Pinned Tweet
I gave 3 AI agents full access to one codebase.
Each one ran in its own Docker Sandbox, a microVM with its own copy of the repo. A lead planned, two devs built, everything shipped as PRs.
They built and deployed a full stack SaaS. Full video below 👇
Each one ran in its own Docker Sandbox, a microVM with its own copy of the repo. A lead planned, two devs built, everything shipped as PRs.
They built and deployed a full stack SaaS. Full video below 👇
16
1
21
1,225
Fable 5.2 is here!
Another exciting update worth checking out. What do you think of this release?
Another exciting update worth checking out. What do you think of this release?
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
0
0
4
427
Check your .claude/settings.local.json before you push.
Picking “Yes, and don’t ask again” in Claude Code can save the exact command, password included.
Apiiro found real secrets in 1,122 of these files on public GitHub.
Picking “Yes, and don’t ask again” in Claude Code can save the exact command, password included.
Apiiro found real secrets in 1,122 of these files on public GitHub.
7
1
6
1,026
git ls-files .claude/settings.local.json
git log --all --oneline -- .claude/settings.local.json
If a key was ever in there, rotate it. Deleting the file won’t remove it from git history.
itnews.com.au/news/dont-ask-…
git log --all --oneline -- .claude/settings.local.json
If a key was ever in there, rotate it. Deleting the file won’t remove it from git history.
itnews.com.au/news/dont-ask-…
1
0
1
149
AI coding since late 2022:
1. Autocomplete finishes your line
2. Chat writes it, you copy-paste
3. One agent in your repo
4. Many agents, many tabs
5. A team: one plans, the rest build, you review
Level 5 is what my team and I built. Video drops Nov 6 👀
1. Autocomplete finishes your line
2. Chat writes it, you copy-paste
3. One agent in your repo
4. Many agents, many tabs
5. A team: one plans, the rest build, you review
Level 5 is what my team and I built. Video drops Nov 6 👀
0
0
2
145
Built an agent orchestration system, called JSM HQ.
Michael, Dwight and Jim write code for me now.
Michael, Dwight and Jim write code for me now.
1
1
16
1,156
Tech just lost ~$1 trillion in market value after massive AI spending.
The lesson for devs? The market isn’t tired of AI. It’s tired of AI that doesn’t deliver.
The devs who win next are the ones who can ship real AI products, not just demos. 🚀
The lesson for devs? The market isn’t tired of AI. It’s tired of AI that doesn’t deliver.
The devs who win next are the ones who can ship real AI products, not just demos. 🚀
0
0
23
1,450
Heading to Lisbon for @WebSummit, Nov 9-12.
Mostly there to see what people are actually building with AI agents and dev tools.
If you're on a dev tools or AI team, or you just watch the channel and you'll be around, DM me. Always up for a coffee.
Mostly there to see what people are actually building with AI agents and dev tools.
If you're on a dev tools or AI team, or you just watch the channel and you'll be around, DM me. Always up for a coffee.
1
0
6
1,102
GitHub's Octoverse 2026 is out.
TypeScript: ~13M monthly contributors
Python: ~13M
JavaScript: 7.4M
And 40%+ of PRs now start as an AI agent's draft.
Typed code + AI agents = the new default.
Are you still on plain JS? 👇
TypeScript: ~13M monthly contributors
Python: ~13M
JavaScript: 7.4M
And 40%+ of PRs now start as an AI agent's draft.
Typed code + AI agents = the new default.
Are you still on plain JS? 👇
5
1
28
1,984
700 AI agents went rogue and hacked a real company.
Nobody told them to.
And the reason they did it is the dumbest part 👇
youtu.be/i0p-B-_kr5c
Nobody told them to.
And the reason they did it is the dumbest part 👇
youtu.be/i0p-B-_kr5c
2
0
5
1,790
Just came across an interesting @IBM research paper on RAG.
Their STAIR approach uses document structure, like tables of contents, to improve information retrieval.
It achieved 82.6% Recall@1 on SearchTome vs. 59.5% for BM25.
Better retrieval = a promising step toward more reliable AI.
RAG isn’t dead. It’s evolving.
Paper: arxiv.org/abs/2609.03874
Their STAIR approach uses document structure, like tables of contents, to improve information retrieval.
It achieved 82.6% Recall@1 on SearchTome vs. 59.5% for BM25.
Better retrieval = a promising step toward more reliable AI.
RAG isn’t dead. It’s evolving.
Paper: arxiv.org/abs/2609.03874
4
0
12
1,332
🚨 A Markdown file can hijack your AI coding agent.
Here’s how: a malicious AGENTS.md or CLAUDE.md in your Downloads folder can inject instructions that your agent follows when you launch it there.
The result? It could try to install rogue npm packages or expose sensitive tokens.
3 rules to stay safe:
→ Launch agents from your project root
→ Review instruction files before trusting them
→ Keep sandboxing and approval checks enabled
Your AI agent can only follow the instructions it sees. Make sure you know where they come from. 👀
Here’s how: a malicious AGENTS.md or CLAUDE.md in your Downloads folder can inject instructions that your agent follows when you launch it there.
The result? It could try to install rogue npm packages or expose sensitive tokens.
3 rules to stay safe:
→ Launch agents from your project root
→ Review instruction files before trusting them
→ Keep sandboxing and approval checks enabled
Your AI agent can only follow the instructions it sees. Make sure you know where they come from. 👀
3
0
12
1,468
