justatdotin

Hi Simon, sorry to spam your comments but 7 months ago you asked me for a media report to back a claim I made and this week it finally arrived. perhaps a little late to be very useful to anyone who maintains that gating function, but here nonetheless:

https://ntindependent.com.au/scientist-says-ministers-pole-f...

speaking of doom,

https://ntindependent.com.au/scientist-says-ministers-pole-f...

now do usa

Tjanara Goreng Goreng did nothing rong.

#LiarDreaming

how is that a personal attack?

a personal attack would be eg calling him a DC.

all I did was point out the intellectual dishonesty of his argument. that's an attack on his intellectually dishonest argument, not his person.

by all means go ahead and ban me

isnt the 1RM the measure of progress?

anywhere you want hard isolation and only a subset of OS. especially multiple instances thereof.

so, generally at the edge (gateways, shims, protocol boundaries)

container can be smaller at rest, but larger at runtime

if you're not sure which you want its probably container

one reason i can imagine for this choice is that human review distributes new knowledge among human maintainers. Automated review might discourage that valuable interaction.

The comment is an artefact of an inherently valuable process, not the sole objective. So I'd prefer code is reviewed by a human who maybe initiates a discussion with an agent. I'd hope this minor workflow detail encourages the human to take a more active lead, rather than risk mere ceremonial approval.

oh yeah well that's an extreme example of how one dev's use could overwhelm a team's capacity.

Hi, the reason I have this expectation is that on a (cognitively) diverse team there will be a range of reactions that all need to be accommodated.

some (many?) devs don't want agents. Either because the agent takes away the 'fun' part of their work, or because they don't trust the agent, or because they truly do not find a use for it in their process.

I remember being on teams which only remained functional because two devs tried very hard to stay out of one another's way. Nothing wrong with either of them, their approach to the work was just not very compatible.

In the same way, I expect diverse teams to struggle with finding a mode of adoption that does not negatively impact on the existing styles of some members.

I think it's mistaken to think in terms of 'falling behind' or 'catching up'

I've seen that these tools have different uses for different devs. I know on my current team, each of us devs works very differently to one another, and we make significant allowances to accommodate for one another's different styles. Certain tasks always go to certain devs; one dev is like a steel trap, another is the chaos explorer, another's a beginner, another has great big-picture perspective, etc. (not sure why but there's even space for myself ;)

In the same way, different devs use these powerful tools in very different ways. So don't imagine you're falling behind, because the only useful benchmark is yourself. And don't imagine you can wait for consensus: you'll still need to identify your personal relationship to the tools.

Most of all, don't be discouraged. Even if you never embrace these tools, there will remain space for your skills and your style of approaching our shared work.

Give it another 10 years and I'm sure this will all become clearer...

it is MUCH easier for solo devs to get agents to work for them than it is for teams to get agents to work for them.

I've shed more tears in the past two weeks than I have in my 40 years of adult life.

forget: there I go again.

kindness beats terror.

I too am an aussie swe (just 3700km up the road) who likes lots of things about working (on a much lower rung) in big (well, mid) tech. I have learned so much more in large orgs than startups, and I'm not done with it.

However:

We DO live in a late-stage-capitalist hellscape.

Large companies ARE run by aspiring robber barons who have no serious convictions beyond desiring power.

I have compromised my principles by giving them (or anyone) my labor.

but I don't lie to myself or anyone else about it. I don't find any need to rehabilitate the structural and personal failings I encounter. When my friends call me out for working at EvilCorp, I don't argue. I know it's like any job: it's all dirty money. Instead, I deal with reality: weigh up pros and cons. I judge each year just how much Corporate I'm willing to swallow to support my dependents.

I enjoy the author's redefinition of cynicism and optimism. These are useful ideas to consider and I've given it some thought, arriving at an attitude of Becoming that I guess some would call idealism.

PS OMFG I just realised its MS. I believe this is what the kids call cringe.

"Fortunately, I’m not that smart." - love that attitude.

multi-agent collaboration on planning is definitely really valuable. I lean in to gemini's long context and have it set up as a long-term observer who I consult about overall direction, project philosophy, patterns in fail and success, and prioritisation. This gives a different perspective from which to assess other agents' plans.

I think it is actually going to happen verrrrry slowly. but it will happen. Many many of my colleagues are understandably resisting. it will take a long time to balance out.

'LM are worse' is really not the strong vote of support you think it is.

More than two things can be utterly disgusting at the very same time!

Unfortunately it means those languages will be the permanent coding platforms.

not really,

I suspect training volume has a role in debugging a certain class of errors, so there is an advantage to python/ts/sql in those circumstances: if, as an old boss once told me, you code by the bug method :)

The real problems I've had that hint at training data vs logic have been with poorly documented old versions of current languages.

To me, the most amazing capability is not the code they generate but the facility for natural language analysis.

my experience is that agent tools enable polyglot systems because we can now use the right tool for the job, not just the most familiar.

yes you've got me, I'm a russian agent trying to fool you into questioning the arms trade.

was it the accent?

ok I think I remember this one where disliking war means I side with whoever you think your enemy is today.

I'm not american and I'm not interested in your ideas about who to kill.

thanks for the correction, I do not want to be aggressive.

I see now I should have just asked: what do you want?

to prefix my response with an admission that I'm not sure what the problem is.

I think I do understand your claim,

which is why I am offering my personal experience as counter-evidence.

agents can empower us to choose the best language for the job, rather than defaulting to one which we are most familiar with.

I suspect our difference in opinion comes from your attitude about tools as a crutch to lean on vs a lever to apply.

I am having a lot of trouble following you. Something has upset you: what would make you feel better?

do you mean that researchers should be disallowed from accessing art?

I do not see how research interferes with all the benefits you prioritise. Can't you continue to enjoy those benefits?

Many people think 'real' music has electric guitars. I think they're wrong, but why argue with them? I think it's fine if you do not like music made from music, but that ship sailed last century. One detail you may be missing is that there are imperfect messy individual artistic humans who make music from music too. Computers are no more an obstacle to human connection through music than electric guitars are.

for me its the arms trade.

Daniel Ek pours spotify wealth into next gen miltech.

sometimes I worry that I don't know what music means to other people but I am certain that to me it is antithetical to war culture.

I would expect more data to make ai music generation better

my experience is that llm programming and rust can fit together very nicely, thankyou.

I am finding agent tooling expands my capacity for multi-language projects

I love ML types, but I've concluded they serve humans more than they do agents. I'm sure it affects the agent, maybe just not as much as other choices.

I've noticed real advantages of functional languages to agents, for disposable code. Which is great, cos we can leverage those without dictating the human's experience.

I think the correct way forward is to choose whatever language the humans on your team agree is most useful. For my personal projects, that means a beautiful language for the bits I'll be touching, and whatever gets the job done elsewhere.

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