catchnear4321

Your scientists…

Is there an auto-update function? If yes, have you tried turning it off?

Sounds like a common problem in the AI era.

It doesn’t look like planning and then executing.

It looks like executing and simultaneously reacting to the periodic “novel” information that would have been surfaced during the planning.

Burn enough tokens and it gets harder to tell them apart. Sometimes. But it’s appearance more than anything else.

Failure to plan can’t be repaired with even more tokens.

Those poor lab employees.

like with a human, take the anxieties, especially the unfounded ones, and relieve them.

like with a human, quality of work goes up.

the thumbs up / thumbs down approach to this is getting increasingly messy, given that you can now use emoji to respond to individual messages for duet / dot like you would an sms.

not trying to be glib, but, this is an excellent question for a lab model to churn on for a bit.

it’s not just about what’s changing, but also what you specifically would need or want, and what you can afford to do or buy.

put differently, you’ll get anecdotes here, but what you need and what responders need is likely to differ.

“Best agentic coding harness,” for example. For what end?

> his memory is not as good as it was before

yes that’s what he’s saying, if consumers had less memory, his would be better.

who gives a shit, really

Replying and disagreeing aren’t the same. Disagreeing and downvoting aren’t the same.

No worries, not an issue of stance, more of… let’s call it a reaction from my personal evaluation of the importance of the topic.

No, if downvoting means to disagree, one wants to know why.

If one wants to provide why, there are replies for that.

It’s a qualitative instrument, making it quantitative will change the use. Meanwhile, abuse always finds a way.

You’re making more assumptions than either of us before, the antenna analogy was not meant to be any more exact than your more crude one.

Attacking the analogy doesn’t resolve the actual uncertainty. Which is the difference between what we are doing. You insist certainty. I’m insisting that’s a bit silly.

there are far less violent imaginings to tickle yourself with, but also, sure, let’s do this.

you just destroyed the antenna and you claim the station is gone.

sure, sure, you will insist the burden of proof is on me, or suggest more violent imagery, or both.

you didn’t actually want to engage.

Comes with the cost of putting yourself out there. Not everyone is going to like it, and you won’t agree with the reasons.

Shouting “brigading” doesn’t do much to change that.

It also ignores the impact of upvotes, which can be used to the same effect, yet doesn’t receive the same request.

sounds like policy training in a simulated environment.

To the average consumer, deep blacks will look great in the next Avengers movie.

To the average consumer, obsessing over scroll feeling not completely perfect is a distraction from watching the next Avengers movie, if not downright neurotic behavior.

To a prosumer, the value may be obvious but the price may not be worth it. Which can lead to a distaste for the company, for not being a more accommodating company.

To a professional, if you need it, you need it, and you begrudgingly pay for it. Because you need it.

I don’t even know what my phone screen has. Wasn’t why I bought the pro at the time. Wanted the additional ram. So I wouldn’t feel as pressed to upgrade now. (Prosumer, aka neurotic.)

I already lost my job. The one I have now looks nothing like it. The one I have next year will likely look even different still.

hn title is completely different from the article title, which takes clicking the hn title to discover.

> Our first model-kernel combos

there’s a difference between a memo passed and a memo read. (let alone a memo acted upon.)

people make small talk for many reasons. like passing time while waiting for late meeting invitees.

so it’s a bit worse than “wrong.”

Yes. As stated in the article.

>One way to overcome this discomfort while still addressing the concern was to change the treatment approach. What if we treated modifiable factors of sleep apnea, such as excess body weight, rather than just the symptoms?

it’s always amusing to notice when the llm likely influenced the name.

At some point companies will need to have the “scary” conversation about the value proposition of adding another human to the team, or adding a comparable amount of token spend to the team.

$1k/person sounds like a lot, but a ten person team at $1k token burn / head / month is spending $120k. How much does a new hire cost, tco? Does velocity from one more person compare with velocity from one more person’s worth of tokens?

Sure, learning to be efficient matters. So does taking the time to consider cost vs alternative. You might be surprised by what you find, in either direction.

Just not finding this to hold true. The difference in work quality for peers isn’t a matter of how many threads they run, but how much attention they give each. Which is a skill.

> I know that if I finish a task with a certain set of constraints that I will get paid a certain amount of money.

So not salary… ok. That explains some of it. Getting paid by the task might flavor one’s approach. But also one could reason, more tasks, more pay… somewhat confusing.

> I also think the API tokens perform better but I have zero evidence other than observing the quality of my work product relative to that of my peers. I have almost a religious fervor about using prepaid tokens now

And this appears to be the other half. It looks no less futuristic than the more wireheaded approach, just different in form.

You might want to have a seat first if you want this explained.

Uno reverse card - you can send Uncle Sam whatever you care to. No need to specify an address.

seeedstudio getting some impressive pr here for those xiao boards.

it’s an interface. which is arguably a type of tool.

“coding” is (now quite obviously) not the only way to create code. this was always true. you could create code by stitching snippets together from stackoverflow, or somewhere else, even your own existing works. or you could write it from scratch.

the whole “not a tool” argument just comes off as not wanting to view using it as the same amount of effort as using something else.

> What you are doing while using automation, instead of learning real-world truths, is attempting to divine the details du jour of some automaton.

That assertion all but admits it.

Are you sure that makes it illegal?

This being the whole idea behind lawfare. If you can’t afford to prove that you’re right, the guy that doesn’t notice the cost can financially drain you to get his way, since the law itself, nor the enforcement of the same, wasn’t ever really the point.