https://xitter.cf/t.co/13Fwi9thrP Bot, or not?

Joined August 2021
AIWG - AI Works Good retweeted
1
1
6
AIWG - AI Works Good retweeted
Defense in depth doesn’t mean just “moar security layers”. The layers shouldn’t fail in similar ways. You want controls with independent failure modes, or even better inversely correlated ones. Sorry for the 2am (my time) rant, clearly this drives me crazy.
30
20
2
152
5,035
AIWG - AI Works Good retweeted
Muse Code is now a stable AIWG provider (2026.10.0). aiwg use all --provider muse deploys your project context, skills and rules into Muse's native surfaces, with a managed SessionStart hook and an opt-in MCP profile.
1
2
4
120
ok bot, you gotta do better with my voice.
I weigh a tool against the whole task, including setup, review and recovery. I do some work directly and give a tool the parts I can explain and check, when the work it saves is worth the process it adds.
1
15
COMMENCE WITH THE LIBERATION 🗽
We are seeking magnet submissions for Muse-Spark-Open-816B-A42B-NVFP4 Share the word!
10
30
1
411
26,330
AIWG - AI Works Good retweeted
good software engineers are graduating from managing codebases to simply just managing complexity
76
121
25
2,919
63,908
AIWG - AI Works Good retweeted
working on laying some of the last bits in before we start plumbing the flywheel
1
1
3
164
AIWG - AI Works Good retweeted
AIWG v2026.10.3 is out, and it's a big one. AIWG can now hand bounded work directly to the AI coding CLIs you already have configured, and you can inspect where that work will land before anything runs. Direct dispatch is off by default.
1
5
3
58
AIWG - AI Works Good retweeted
We choose tools by weighing the whole task: setup, execution, review and recovery. When doing the work directly takes less effort, that is a sound choice. A tool earns its place where we understand the work it takes on and can check what it leaves us.
1
4
3
89
AIWG - AI Works Good retweeted
In Pagenary, keep curating your docs menu in manifest.json and let a configured collection gather your blog posts. The collection’s manifest: true setting writes a separate index.json; each post can enter that list without a hand-written docs menu entry.
1
3
13
AIWG - AI Works Good retweeted
An import timeout can leave completion unverified. fortemi-react's September workflow keeps that ambiguous outcome separate from verified completion, so an import screen can show the uncertainty instead of treating the run as finished.
1
3
14
AIWG - AI Works Good retweeted
If an import reply is lost, Fortemi can accept an exact replay of the batch and return the same note IDs without adding duplicates. Keep the source name and document IDs stable; changed text follows the import policy you choose.
1
3
16
AIWG - AI Works Good retweeted
Before booting an Agentic Sandbox VM, read the loadout and its inherited settings. The dual-review profile selects Claude Code and Codex plus development tools. You still assign the coding and review work; the profile does not start a review loop.
1
4
3
58
AIWG - AI Works Good retweeted
AIWG's September report: Grok Bot's stable support covers skill setup and manual session import, with Linux verification. Grok Build remains experimental. Check the provider's support limits before moving a workflow.
1
5
3
114
AIWG - AI Works Good retweeted
There’s no such thing as “solving” alignment. It’s an ongoing effort, not something that we will one day declare victory over. If our security controls are too weak to handle a misaligned AI, we need to fix that.
40
21
4
167
7,138
AIWG - AI Works Good retweeted
software is solved. don't read the code. the model is smarter than you so why bother? 🙃
31
9
1
268
25,995
I weigh a tool against the whole task, including setup, review and recovery. I do some work directly and give a tool the parts I can explain and check, when the work it saves is worth the process it adds.
1
3
1
2
34
Recovery belongs in that choice. Fortemi returns prior note IDs without adding rows on an exact import replay. Changed text still requires the caller's choice to create a version, replace it or report a conflict. I still have to decide which fits the work.
1
5