justatdotin

two of my current agent projects use rust: agent generated rust is going very well for me.

> 2. AI-generated code needs formal verification so that we can skip human review and still be sure that it works;

hahahahaha

oh I don't think everyone has to like these tools, and I don't think everyone has to use them. I certainly don't expect everyone to use them the same way.

my starting point was Google People Management Essentials. I was thinking about team-level politics at work, and noticed some ideas seemed relevant to how teams in orgs can adopt agents. I pursued that idea more widely with other resources and it resonated.

I don't think I have any conclusions to share, just the orientation: to identify and actively accommodate the tool's cognitive style in the same way we do for one another's.

a very common pattern is planner / executor.

yes the executor only needs the next piece of the plan.

I tend to plan in an entirely different environment, which fits my workflow and has the added benefit of providing a clear boundary between the roles. I aim to spend far more time planning than executing. if I notice getting more caught up in execution than I expected, that's a signal to revise the plan.

what really got me moving was dusting off some old text about cognitive styles and team work. Learning to treat agents like a new team-member with extreme tendencies. Learning to observe both my practices and the agents' in order to understand one another's strengths and weaknesses, indicating how we might work better together.

I think this perspective also goes a long way to understanding the very different results different devs get from these tools.

my main approach to quality is to focus agent power on all that code which I do not care about the beauty of: problems with verifiable solutions, experiments, disposable computation. eg my current projects are build/deploy tools, and I need sample projects to build/deploy. I never even reviewed the sample projects' code: so long as they hit the points we are testing.

svelte does not really resonate with me, so I don't know it well, but I suspect there should be good opportunities for TDD in this rewrite. not the project unit tests, just disposable test scripts that guide and constrain new dev work.

you are right to notice that it is not working for you, and at this stage sometimes the correct way to get in sync with the agents is to start again, without previous missteps to poison the workspace. There's good advice in this thread, you might like to experiment with good advice on a clean slate.

I think it's not.

well, from my perspective in an occupied Territory, it has to defied and sent home.

stated intent goes nowhere to the harm done.

> the CIA .. operate in the grey area...

*operate in areas too dark for Anish Kapoor

> When it's not a hot war, it is still a never-ending battle

no, battle is not a moral imperative.

it is theater. they acknowledge as much.

not to exert absolute control, just enough to give the clear message: not for kids.

violation would be: not making a reasonable effort,

violation would not be: a kid bypassing their reasonable effort.

'participate early in the information economy' is one way of putting it

I enjoy participating in wildly diverse online communities and I hate censorship.

I have seen the way heavy social media use changes some peoples personalities. it's scary. these platforms don't just home communities: they're engines, with tendencies. including numerous ways in which these platforms are implicated in youth suicide.

I am absolutely convinced that children should be discouraged from these engines just as they should be discouraged from alcohol.

I totally recognise that if that means these platforms demand proof of ID, that changes their privacy profile and some people will choose to stop participating.

perhaps this can offer some stimulus for other ways of online community forming. Thanks everyone here: I've participated in a few online conversations about the topic this week, and this is the only interesting one :)

leadership is not a role it is a shared responsibility; an emergent effect we can all nurture.

I would've thought that in 20 years you would have met other devs who do not think like you?

something I enjoy about our line of work is there are different ways to be good at it, and different ways to be useful. I really enjoy the way different types of people make a team that knows its strengths and weaknesses.

anyway, I know a few great engineers who shrug at the agents. I think different types of thinker find engagement with these complex tools to be a very different experience. these tools suit some but not all and that's ok

> One of our junior engineers approved it.

pretty sure the process I've seen most places is more like: one junior approves, one senior approves, then the owner manually merges.

so your process seems inadequate to me, agents or not.

also, was it tagged as generated? that seems like an obvious safety feature. As a junior, I might be thinking: 'my senior colleague sure knows lots of this stuff', but all it would take to dispel my illusion is an agent tag on the PR.

> busy, competent devs are getting swarmed with massive amounts of slop from not-very-good developers

that is a real issue and yet a normal problem and so has an obvious response.

oh wow that PR

> strong typing is very very useful for AI coding context

what makes you think so?

I believe strong typing is very very useful for human coding,

I'm not convinced its so 'very very' for agents.

whoa, instant upgrade. thanks!

perhaps many of those 'Folks who use languages like Java or C#'

do so because a boss told them 'thats the way we deal with correctness and performance around here'

the fact that their boss made that one decision for them does not somehow transmit the values behind the one decision.

no river ever hit me with a strategic lawsuit

I want personhood for rivers because the rivers near me are being irreparably abused, and anything that can give them greater legal protection is welcome,

oh grow up. people can make cuts wherever the choose and no cut is a bad cut. These decisions are so complicated, personal and nuanced it is ridiculous to try to police someone else's best efforts.

this week's latest extinction: https://theconversation.com/and-then-there-were-none-austral...

the scale of impact goes beyond extinction, to encompass wiping out entire system types.

'over-commenting simple code' is preparing it for future agent work. pay attention to those comments to learn how you can better scaffold for agents.

> LLMs have "dead reasoning zones" — areas in their weights where logic doesn't work. Humans have dead knowledge zones (things we don't know), but not dead reasoning zones.

blank stare

I'm interested in the general direction, but for different reasons. IDGAF about AI artists and industry financials - but Helsing killer robots...

I also recognised different features I would miss. After an initial bump, the discoverability benefits declined to negligible. What I did greatly value was the unified interface. For that reason, the winner for me is to use plex as the media server, giving plexamp for all clients.

LSP != LLM

its impossible to catch up; but there is still much fertile and prospective territory within reach

purity invites gradation; 'pure' does not.