The whole point of the omni-context is that you are putting yourself in a space where you have to act in a way that is appropriate to all of those places.

I would say things in the Bar that I would not want the reverend, my grandmother or my children to hear - but in the uni-context I have to mediate my speech to what is appropriate to all of those audiences or risk judgement for it.

The uni-context discourages expression. It's like a dystopia where everything you say and do is recorded and can be recalled for judgement at any time. And yet people sign up for it.

Trying to maintain separate context, different identities across platforms is an attempt to fight against that and to limit the risk that something I say on one plaform is not going to destroy my social credit in every other platform where I participate.

1. You have a task and it requires an expert to perform it (software engineering, where we were) 2. You automate the task, it still requires the expert to babysit it (where we are now) 3. Management works out that the expert is just monitoring what the automation is doing and has actually lost expertise because they are just watching, not doing. Pay collapses. (where we are going)

Source: https://en.wikipedia.org/wiki/Ironies_of_Automation

If AI wearables could help them navigate unfamiliar places, identify and read signs or answer questions about their surroundings I think they would leap at it.

But you want to focus on one end of the spectrum? Yes, it's the truth but not the whole truth.

So the elite users are the ones who choose. Funny how our communities mirror the social structures we supposedly hate.

But yes, the original poster with their allusions to lost limbs and "pointless swinging in a vast, unquantifiable emptiness.." is overreacting, depressed or both.

The slop will continue until it is no longer profit-making for someone.

I ask, not to condemn, but to find out what your process was for developing the requirements. Clearly it was done with LLM help but what was the refinement process?

Generally its feature a, feature b and a refactoring branch of some kind.

My workflow is:

1. Add ticket in gitlab describing bug or feature in as much detail as possible along with acceptance criteria like expected unit tests or browser based tests.

2. In a work tree create a branch based on the id of that ticket in gitlab.

3. Start Claude, tell it to use a skill to pull that ticket, research and make a plan.

4. Review the plan, ask questions, refine.

5. Approve plan and let cluade cook.

6. Have Claude run a set of linters/tests/code quality checks and ground until done.

7. Start a new Claude instance, ask it to review changes made. Provide feedback to first Claude instance for changes.

8. Commit and push, creating a draft mr/pr in gitlab.

9. Review the actual code changes myself using gitlab. Comment on things not right.

10. Get Claude to use another skill to pull comments and work to resolve them. Also feed back any CI failures.

11. Manually close comments and push again. Repeat until done and ready for co-worker review.

I can only keep 3 threads like this going at once. Sometimes it’s only 1 or 2, depending on complexity. Smaller is better. Try to stay atomic and avoid feature creep in each mr.

Username checks out, but you might want to check with your mother about how she feels about this comparison.

TFA brings up abuse not stndef.

An analogy is "a thing which is comparable to something else in significant respects" and stndef is right to point out that microsoft behavior, while abusive, is not comparable to domestic abuse "in significant respects". Not even close.

The TFA title is sensational for effect and in very poor taste.