I wish I could be that happy. I have two V8s and both of them are prone to becoming stinky. Changing out the filters doesn't help, and dismantling and cleaning out the interior does make it better ... for a time. Then the smell comes back.
But for a cordless stick vacuum I do like the basic design. For real vacuuming I choose my Sebo E3 every time, but it's not nearly as quick to use as a cordless stick.
One of the best things you can do for a Dyson stick vacuum, in my humble opinion, is get an adapter so you can use something like a Milwaukee tool battery.
Sure, he should just have lived as a slave and not socialize with anyone until he left.
H1Bs have been used as a path to citizenship for a long time. You can't just change the rules like that without destroying so many lives in a senseless act of cruelty. But the cruelty is the point.
Is it not cruel to Americans to replace them with said slave labor through legislation? The people who built this prosperous modern nation that so many people wish to flock to for a better life are just kicked to the curb -- talk about cruel.
* America was built by pioneers and colonists who tamed the wild continent and helped create the modern civilization we enjoy. They brought their experience and culture from the Western civilization from which they were launched.
* There are Americans currently alive who are direct descendants of the pioneers and colonists who created this great nation who deserve to prosper from their ancestors' sacrifice(s)
* Resources (housing) and opportunities (jobs) are finite -- if Heritage Americans have to compete with the entire developing world for their birthright, there is a non-zero chance they will be "kicked to the curb" so to speak.
Nah, Cell Broadcast has a lot less overhead since it does not have to do any routing or delivery confirmation and such. The load does not scale based on recipients which makes it far more reliable during an emergency.
Sorry, maybe I did "carrier replication" wrong - I used the word in a sense of "it is duplicated at the local cell by the towers", instead of getting "fed with 1mio receivers in region X by the telco servercentral HQ"
Cell broadcast, depending on the emergency level set by the sender, also makes your phone vibrate until you read the message, and may also cause it to play a loud siren noise. Which is the sort of thing you want in a real emergency.
Because it doesn't do the job well. It's difficult to send any media, group chats are a pain, international messages often incur fees, it doesn't work on wifi-only, and so on.
To be fair, it’s not unreasonable to take your safety for granted when in the presence of the US president. I do find it odd Trump decided to go though.
It doesn’t have to be a foregone conclusion that GLP-1 causes muscle loss though. The primary reason for the muscle loss is the reduction in calories and protein intake. If you want to keep most of your muscle mass you can just make sure you keep up with your daily caloric and protein needs.
Muscle requires protein, yes. Unfortunately, we don't get to keep unnecessary muscle just by eating protein. The body requires a lot less muscle to lug around 200 pounds than it did when lugging around 300 pounds.
We have to do the strength training. "Use it, or lose it".
exactly. Usually legacy code forms when people lose context and confidence in parts of the codebase due to staff turnover etc and ppl avoid touching or enhancing those parts for long periods. Six months is a short time to accrue that much tech debt, its enough time where most of the people who created that "legacy" are probably still around. As you said indicates bigger problems.
It's a fair point, it's not truly unlimited and I do wonder how that would change my workflow. I can definitely imagine if I was inside Anthropic or OAI with unlimited "fast" tokens, you would be more tempted to hand over even more of this process. I completely understand why they talk about "graph engineering" and such, my entire workflow above could be a graph and I could try to increase my leverage even further. Realistically though I am bounded by product decision making, not code output right now.
This! I don't think folks understand how easy it is to go from greenfield to brownfield with these tools, esp if your organization is only valuing velocity. Meaning your doing full agentic development on large features, barely reviewing any code, and shipping without much refinement. It's insane, but this appears to be the status quo in SF startups.
Something isn't clear about the size of your codebase here and the level of reliability your customers expect, as a reader of your comments. Clarity there will help.
My observation has been:
- Initial greenfield work by an LLM is fast and very effective with minimal or no human oversight.
- Subsequent work ends up being over engineered and very verbose. Assumptions are made that aren't suited to the problem at hand (for example I find Fable is extremely regex happy where structured data would work much better from a readability perspective.)
- Once code bloats beyond a certain point due to unguided LLM usage, complexity is high enough that only LLMs can operate on the codebase with any economical amount of time.
- Rinse repeat and your code ends up unclear about any state that's not explicitly being tested and verified in QA loops
For some of our products this has been fine, for others it's been problematic. An understanding of your size and reliability requirements will help make the conversation more productive.
Why aren't you guiding your LLM usage? Is that what I said - to spam it and not guide anything? Or to have a careful workflow where you agree on design and maximize your human judgement/leverage?
> any state that's not explicitly being tested and verified in QA loops
As opposed to before, when engineers perfectly reasoned about code behavior from first principals and QA was unnecessary?
> Why aren't you guiding your LLM usage? Is that what I said - to spam it and not guide anything? Or to have a careful workflow where you agree on design and maximize your human judgement/leverage?
You didn't say anything positively or negatively regarding this so I made an assumption that you were using the LLM relatively unguided (e.g. a bit of oversight, not the kind of thing that heavy code reviews used to involve pre-agents.) Feel free to add clarity on your actual usage loop.
> As opposed to before, when engineers perfectly reasoned about code behavior from first principals and QA was unnecessary?
In my experience, most engineers are quite good at reasoning about code behavior for non-QAed code paths. Obviously things fall through the cracks. But I've been in the ground floor of plenty of Big Techs in their early stages before agents and, yes, a lot of initial development had spotty test coverage and yet most of the engineers had good mental models of what was happening. It used to be a very valuable skill to wrap your head around a torrid piece of code with few or no tests but was nonetheless a core piece of your application. Conversely, agentic development can bring cognitive debt [1].
===
This isn't a fight. We aren't sparring over what's right and wrong. I'm just curious how other people use agents in their work as someone who is also now in a startup that uses LLM agents heavily and has no limitations on spend.
> You didn't say anything positively or negatively regarding this so I made an assumption that you were using the LLM relatively unguided
I feel like this statement betrays your lack of advanced experience coding with LLMs.
OP's elaboration of the steps they are going through (planning, agreeing on plan, getting one LLM to draft execution plan, approving it, then executing with a separate LLM, then reviewing/testing) made it super obvious to me that they are guiding their LLMs quite considerably as part of their work.
Anyone making blanket statements about LLMs producing garbage is just telling on themselves about not having proper SDLC practices in place.
Planning, agreeing on a plan, separating planning and implementation LLM, using separate review LLMs, these are all table stakes. This isn't "guidance" if you're getting paid to write software. If you think "unguided" means "I typed a prompt into claude code and waited yolo" I don't know what to say but, you have a very different idea of what professionals do than I do.
I find for my own work that I need to read the diff the LLM produces then offer feedback on the diff in its own loop before I am satisfied, and this is after all the unattended QA steps through Codex Computer or Claude MCPs happen. Then auto reviewers come in and then reviewers come in. Of course, at our stage, we rarely have this luxury and it's only reserved for the very core of our codebase.
This is still much less guidance than we used to do for code before agents became popular. Even at Series A companies, before agents, we used to socialize tech specs, get buy-in from multiple engineers, create test plans, etc etc.
> Anyone making blanket statements about LLMs producing garbage is just telling on themselves about not having proper SDLC practices in place.
> I feel like this statement betrays your lack of advanced experience coding with LLMs.
Are we in school debate club? I don't know what's going on lol, I'm just curious how people are using LLMs! Is it just that irresistable to take a cheap shot at each other?
Not that I know of but that's the conclusion I drew from your statement.
It's not a cheap shot unless you took it personally?
I suppose I could have said "the fact that OP's explanation of how they work did not lead you to conclude they were in fact guiding their LLM usage quite a bit tells me that perhaps you have not been working with LLMs in any advanced capacity".
For the SDLC comment I admit it was a broader statement (based on observing people generalizing that "LLMs produce bad outputs") and not specifically aimed at you, and I didn't make that clear, so my bad.
> If you think "unguided" means "I typed a prompt into claude code and waited yolo" I don't know what to say but, you have a very different idea of what professionals do than I do.
Not having human input in the loop, i.e. allowing agents to act without guidance. I understand the idea of having agents guide agents, but really how much do we gain when Sol scolds Fable?
I use it. We have more workstreams than people and so we have to rely on this pattern for most of our new products, but I still find the code doesn't meet my bar. To me it produces passable but not good, maintainable code. Good enough for our experimental products with the cognitive debt associated with heavy agentic development. We take this calculated tradeoff of velocity for cognitive debt and middling quality because we're a startup and we feel that velocity matters more than correctness, but that is just a bet as the nature of startups go.
AI is an accelerate tool for any organizations, management thinks it'll solve their organization issue because it accelerates it. Most often, it accelerates toward a wall.
Design is too expensive, we do agile.
QA too expensive, we fire all of them, and claim devops is the now, which allows us to fire the Ops team too, 100% ownership from deisng to ops on devs.
One person with an agent can replace all these teams. Yeah mo profits.
What is the point of working at a startup if you’re dealing with millions of lines of legacy code ? Isn’t the whole point of startups to create & innovate with a clean slate and modern tools?
How long has your startup been around? I’ve worked at plenty of startups over the past 20 years. Including one that was still calling themselves a startup 10 years out. The org I work at now was a startup before my tech giant employer acquired them. We have a very bloated and very profitable 8 year old codebase that is barely 500k LOC.
I’ve never seen a startup with a multi million line legacy codebase.
In response to a question about a legacy codebase at a startup. That implies that they think whatever they are doing is common. And forking a multi million line codebase and heavily developing it isn’t common for startups.
I don't know if that's the whole point, but I agree with the sentiment, why would a startup be working in legacy code and where would that code come from if this is truly the start of something.
OP might just be working at a small software company or for one that broke from a bigger one and is now "startup" like?
You'd be surprised. I met a guy last week who was proud to tell me he had vibe coded an almost 2 million line code base. The app did not sound that complicated, so I'm assuming it's full of copy-pasta flavored slop.
reply