Yesterday (pro plan) I ran one small conversation in which Claude did one set of three web searches, a very small conversation with no web search, and I added a single prompt to an existing long conversation. I was shocked to see after the last prompt that I had somehow hit my limit until 5:00pm. This account is not connected to an IDE or Code, super confusing.
Everyone who has not hit this bug thinks it’s user error… It’s not. It happened to me a few days ago, and the speed at which I tore through my 5 hour usage cap was easily 10x faster than normal.
Also: sub agents do not get you free usage. They just protect your main context window.
There are more PE firms than there are McDonalds in the US. Most of them exist to buy solid companies where ownership wants to cash out or fixing failing cash-poor businesses with good bones.
PE has become shorthand for "thing I don't like", and admittedly there are a lot of horrible evil people in PE. As a concept though, it's pretty benign.
PE is a very broad practice. It's kinda hard to make a single-blanket argument for it (it's like asking "Is Software good for society?" Yes, maybe?).
So here are some positive things that I think PE funds can contribute:
1) Private equity serves as an exit path for small business builders. Suppose that you have built a small, profitable trucking company. Now you are old and want to retire. You kids have no interest in the business, and have already built different careers elsewhere than managing a fleet of Super Greats. Oftentimes, PE funds are only realistic buyers of your business.
2) At a more subtle level, PE can supply better management. For example, a supermarket owner I know accepted capital from a PE fund specifically to acquire better talent (his remark: "very talented people are rarely excited to operate a rural food & beverage shop").
3) PE-backed companies are, arguably, structurally better than the public counterparts. The cliche is that many public firms are run like third-world fiefdoms (the board are focused on empire building; the executives are spending money lavishly on perks). Most of these concerns vanish once each director are given a shared, transparent objective set by the deal structure. (As Henry Kravis often remarks, PE is mostly about alignment of the interests)
Private equity is just a type of investment. It can be run by scumbags or regular people.
The growing role of PE in everything and everywhere is IMO a symptom of wealth inequality. PE didn't invest in veterinary practices, retirement homes, or plumbing businesses 30 years ago. They're just running out of places to put all that cash.
Broadly speaking, private equity is used to describe anything leveraged we don’t like. When we like it, we tend to describe it as a start-up, family business or simply “firm.”
Hey, it's you again! I was wondering if you would pop up in the comments defending private equity as you've done in the past.
Continuing our discussion from last time, can you elaborate on why you think quoting Revlon is sufficient to excuse the practical differences between public and PE companies?
I had worked with PE firms for over 6 years from the other side where we would invest in PE funds operating primarily in emerging markets, about 50 or so during my time and reviewed another 50 more that we did not invest in. Most of them are pretty benign. We invested primarily in transportation, energy and infrastructure but also hospitality and industry. There are many many poorly run private companies out there that PE funds buy out and rehabilitate. One major segment for a couple of funds is the purchase of poorly run family businesses where the founder was successful because they had drive and energy and built something at the right time (or sometimes, they knew the right people) but lacked the interest or vision to take it to the next level. Or the founder is getting old and the family has managed to turn the once successful business into a money loser. This is a long about way of saying, the majority of PE firms are benign and have invested in many successful businesses that many of us use. There are bad actors and more so in the US where corporations are allowed to eat the weak. It is not a case of PE bad but much more so that US business laws have relatively weak protections for consumers.
> > There is a legal requirement for directors of public companies to act in the financial interests of all shareholders
> No, there isn't.
The whole point of Revlon duties is that they trigger "in certain limited circumstances indicating that the 'sale' or 'break-up' of the company is inevitable" [1]. Outside those conditions, "the singular responsibility of the board" is not "to maximize immediate stockholder value by securing the highest price available."
I'll leave it up to you to recontextualize with the remainder of that thread if you want to continue discussing.
Within that context, what's confusing you? And where did I argue that "quoting Revlon is sufficient to excuse the practical differences between public and PE companies?"
Revlon duties are a specialised duty that apply in certain circumstances. They don't in others. The other situation is what we were talking about; herego, those special duties don't apply to the other situation, which is part of the general situation. It's an old piece of rhetoric [1].
If you're consistently getting downvoted in a thread, and the other side getting upvoted, try re-reading it instead of presuming sanctity. Especially if you haven't worked in a field, are mixing up terminal and are e.g. citing legal argument about a private company to make arguments about a public one (Ford).
> If you're consistently getting downvoted in a thread, and the other side getting upvoted, try re-reading it instead of presuming sanctity.
Lol, what a humble take. We all know in this VC owned forum that only truth is upvoted, and lies downvoted, especially on topics like private equity.
> Revlon duties are a specialised duty that apply in certain circumstances. They don't in others. The other situation is what we were talking about
Again you're operating insincerely, because as I told you last time, and this time, Revlon does not relate to what I'm referring to. I even quoted you Dodge v Ford Motor Co as a jump off point for your education, which you refused to acknowledge due to it being "from over 100 years ago".
Anyways I'm curious if you'll share your background, and why you're consistently in these discussions about private equity, rabidly playing defense?
Private equity is good for society because it provides a financial incentive for owners of the equity to increase the value of a company. The value of a company is tied to how much value it provides society. Financial incentives do work in practice in affecting behavior in humans. Especially with the scale that some companies can reach. In conclusion the concept of privately held equity existing accelerates the betterment of society.
Facebook and others have been scanning your private messages for many years already. Then someone discovered that this practice is illegal in Europe. So they passed the temporary chat control 1.0 emergency law to make it legal. The plan was to draft a chat control 2.0 law that would then be the long-term solution. But negotiations took too long and the temporary law will expire on the 4th of April (not the 6th) which means that it will be illegal again for Facebook and others to scan the private messages of European citizens without prior suspicion of any wrongdoing.
My impression was that the temporary permission-granting regulation was passed before the relevant privacy law came into effect, but I didn't check the dates now.
Well, chat control 1.0 is about making an existing practice legal, it didn't create the practice of scanning messages for know child sexual abuse material, though I don't know how long that has been going on before the legislation in 2021 passed (but probably for several years at that point, since getting a new law trough takes a while).
The data that isn’t flagged from scanning is prohibited from being stored in the first place. Flagging is required to have maximum accuracy and reliability according to the state of the art. Data that was flagged is stored as long as needed to confirm (by human review) and report it. Data that isn’t confirmed must be deleted without delay.
The haptic sensor is almost as good as the physical button, and the trade off of not having to worry about it breaking (which was likely after a few years with the physical ones) is well worth it for me.
Strongly disagree with this. Bad junior devs might be useless, but I’ve seen good ones absolutely tear through features. Junior devs fresh out of school typically have tons of energy, haven’t been burned out, and are serious about wanting to get work done.
Some of you folks think way too highly of yourselves. Junior devs are awesome. You tell them what needs doing, if it's not well defined you have them write a document to figure it out, and then they churn away at it and will often surprise you with a brilliant solution.
Meanwhile, I've never once seen a coding agent give a brilliant solution or design to just about anything, and anything with the barest whiff of undefined-ness will simply zero in on your existing biases.
This whole thread reads like absolute insanity to me. I love getting new junior devs. They do great work.
Or do the same for IAC - same surface area - and use Terraform on one project, CloudFormation on another, and the CDK on a third and to generate code for you when you give them the correct architecture. It took me a day to do that before AI depending on the architectural complexity and I know AWS well (trust me on this). How long would it take me to delegate that to a junior dev? It took ChatGPT 2 minutes before I started using Claude just by my pasting a well labeled architecture diagram and explaining the goal.
It took me about 8 hours total to vibe code an internal web tool with a lot of features that if I had estimated before AI, I would have said a mid level developer would have taken two weeks at least. It wasn’t complex - just a CRUD app with Cognito authentication. How long would it have taken a junior developer?
The one reason I can't care about these kind of arguments is that you're describing the solution, not the problem. Based on my career (maybe shorter than yours), usually you put juniors on projects of low complexity and low impact while you play the mentor role. It's not about them being a productive worker or a menial helper, it's for them to train using practical projects. Your problems don't look like suitable projects unless you want them to train them in copy-pasta from the Internet.
Junior - everything is spelled out in excruciating detail, the what and the how. They are going to be slow, not know best practices, constantly bug other developers and you srs going to have to correct them a lot.
Mid level developer - little ambiguity on the business case or their role in it. They are really good coders in their domain. They have the experience to turn well defined business requirements into code. You don’t have to explain the “how” to them just the what. They should have the ability to break an assigned “epic” based on the business requirements to well defined stories and be a single responsible individual for that Epic maybe working with juniors depending on the deliverable or other mid level developers.
A senior developer works at a higher level of ambiguity and a larger scope, the business may know they want something. But neither the business or technical requirements are well defined. Think of a team lead.
Senior+ - more involved with strategy.
If I have to define everything in great detail anyway, why not just use AI? It can do it faster, cheaper, more correct and the iteration is faster. I would go as far as saying in my recent coding agent experience, a coding agent is realistically 100x faster than a junior developer since you have to give both of them well defined tasks.
My experience with Claude code and codex recently is that even the difference between a mid level developer and a coding agent is taste when it comes to user facing development, knowing funky action at a distance, and knowing the business, with a mid level developer you can assume shared context and history with an ability to learn.
So again, why do I need to hire a junior developer in the age of AI?
As an Entry Level Engineer, you’ll be expected to develop and maintain lower complexity components under the guidance and tutelage of more experienced team members.
That does not really contradict my point.
> If I have to define everything in great detail anyway, why not just use AI?
You don't have to define everything. And to do so is detrimental to their growth. If you're their mentor, you're supposed to give them problems, not recipes. And guidance may be as little as an hint or pointing them to some resource, not giving them the solution outright. The goal is not to get a problem solved (that's just a nice-to have), the goal is to nuture a future colleague.
Why should I hire a junior who doesn’t know the what or the how. Instead of hiring a mid level developer who could be an excellent developer who can turn business requirements into code and is more than likely better at certain things than I am since they live and breathe it everyday and can both do the work without supervision and can offer valuable advice and say something that might convince me that I didn’t think things clearly?
Reminding you that the difference above a mid level developer and a “senior”/“senior+” is scope and ambiguity not necessarily technical depth in one area.
What does a junior developer bring to the table that I should use my open req on?
1- You need a ton of internal knowledge so it doesn't really matter what they know past the basics.
2- Testing gets expensive with seniors
3- You can't get mid-senior level employees you like. I see very often companies having really high requirements for hiring leading to the only candidates passing being friends of employees. Juniors pass easier via the 'he's motivated to learn' path.
4- Juniors bring a motivation with them. Seniors tend to generally care less so a couple of energetic juniors can get them moving a bit quicker. Especially if you find a good one, since a senior really doesn't want to get outperformed by a fresh graduate. Also, since they usually suck at politics, it's easier to prod them about why things aren't working than the seniors who've played the blame game for 20 years and have perfected the art of dodging responsibility.
> Why should I hire a junior who doesn’t know the what or the how.
I'm not saying you should. It's the business model that will answer that question. But the traditional wisdom was that juniors are not costly and have few obligations tying them down. And juniors don't stay junior.
And some may know the what and the how, at least technically. What they may lack may be just how to develop their skills further to be useful in a professional settings. It's easy to learn programming languages, tools, libraries and frameworks when you have a lot of free time. And they're not asking to be your protégés, you're just training them to be useful for your team.
Design a concurrency implementation? I sure hope they would spend more than 3 minutes on it! Concurrency lends itself to subtle bugs even when experts write it.
I'd gladly take a junior dev to do any of that work there, because they can think for themself and not hang onto any bias you unknowingly build into the prompt like it's a religion.
I can absolutely guarantee you that a junior dev or even a senior dev could do complicated IAC as fast as AI. It isn’t that knowing the architecture is the problem, it’s just very tedious. You have to look up all of the properties involved for each service and each property of each resource. I trust AI to know proper AWS architecture from being trained on the total corpus of the internet more than a junior dev.
And it’s not a waste of their time to have to give detailed requirements and troubleshooting steps to a junior developer, constantly being interrupted, and then having to check their work thoroughly?
If you have to be that detailed anyway - you might as well use AI.
So exactly how am I going to convince my management to open a req for a junior developer who is not going to help us meet our quarterly goals and take time away from the other senior developers that will either have to work longer hours or do less work?
I’m not going to work as a charity and neither are any of my coworkers. We are all here to exchange labor for money.
We as a collective need to convince our management of this, but that needs to start with people getting their heads out of their asses and working together instead of this mercenary attitude you have
I don’t have to do anything except keep my head down, do my job and enjoy my well earned autonomy. I’m definitely not going to try to convince my skip, skip, skip manager to change their hiring policies. It’s not like my line level manager has any power over anything
Even when I was at a startup before 2020 and I did have the ear of the CTO and the founders I knew my ultimate mission was to do what was needed to get acquired and before that I knew exactly what my mission was when k was hired to lead the tech initiatives as we were acquiring companies “find efficiencies” and go public.
Or do you think I could have convince anyone of anything as an L5 at AWS in the middle between architect at a startup and my current company?
Your getting unnecessarily down voted by devs who want to feel morally superior, but don't have any concrete answer to the conundrum you've posed.
It's about money, and the actual solution would be to lower pay at senior level and give it to juniors, with some lock in agreed by the junior in exchange for this grace.
They're getting downvoted because they are a miserable misanthrope, and it is our responsible as people in a society to punish obviously antisocial behavior.
Agree. I’d like more fine grained control of context and compaction. If you spend time debugging in the middle of a session, once you’ve fixed the bugs you ought to be able to remove everything related to fixing them out of context and continue as you had before you encountered them. (Right now depending on your IDE this can be quite annoying to do manually. And I’m not aware of any that allow you to snip it out if you’ve worked with the agent on other tasks afterwards.)
I think agents should manage their own context too. For example, if you’re working with a tool that dumps a lot of logged information into context, those logs should get pruned out after one or two more prompts.
Context should be thought of something that can be freely manipulated, rather than a stack that can only have things appended or removed from the end.
Yeah, the fact that we have treated context as immutable baffles me, it’s not like humans working memory keeps a perfect history of everything they’ve done over the last hour, it shouldn’t be that complicated to train a secondary model that just runs online compaction, eg: it runs a tool call, the model determines what’s Germaine to the conversion and prunes the rest, or some task gets completed, ok just leave a stub in the context that says completed x, with a tool available to see the details of x if it becomes relevant again.
That's pretty much the approach we took with context-mode. Tool outputs get processed in a sandbox, only a stub summary comes back into context, and the full details stay in a searchable FTS5 index the model can query on demand. Not trained into the model itself, but gets you most of the way there as a plugin today.
This is a partial realization of the idea, but, for a long running agent the proportion of noise increases linearly with the session length, unless you take an appropriately large machete to the problem you’re still going to wind up with sub optimal results.
Yeah, I'd definitely like to be able to edit my context a lot more. And once you consider that you start seeing things in your head like "select this big chunk of context and ask the model to simply that part", or do things like fix the model trying to ingest too many tokens because it dumped a whole file in that it didn't realize was going to be as large as it was. There's about a half-dozen things like that that are immediately obviously useful.
Oh that's quite a nice idea - agentic context management (riffing on agentic memory management).
There's some challenges around the LLM having enough output tokens to easily specify what it wants its next input tokens to be, but "snips" should be able to be expressed concisely (i.e. the next input should include everything sent previously except the chunk that starts XXX and ends YYY). The upside is tighter context, the downside is it'll bust the prompt cache (perhaps the optimal trade-off is to batch the snips).
So I built that in my chat harness. I just gave the agent a “prune” tool and it can remove shit it doesn’t need any more from its own context. But chat is last gen.
Good point on prompt cache invalidation. Context-mode sidesteps this by never letting the bloat in to begin with, rather than snipping it out after. Tool output runs in a sandbox, a short summary enters context, and the raw data sits in a local search index. No cache busting because the big payload never hits the conversation history in the first place.
> I think agents should manage their own context too.
My intuition is that this should be almost trivial. If I copy/paste your long coding session into an LLM and ask it which parts can be removed from context without losing much, I'm confident that it will know to remove the debugging bits.
I generally do this when I arrive at the agent getting stuck at a test loop or whatever after injecting some later requirement in and tweaking. Once I hit a decent place I have the agent summarize, discard the branch (it’s part of the context too!) and start with the new prompt
> For example, if you’re working with a tool that dumps a lot of logged information into context
I've set up a hook that blocks directly running certain common tools and instead tells Claude to pipe the output to a temporary file and search that for relevant info. There's still some noise where it tries to run the tool once, gets blocked, then runs it the right way. But it's better than before.
I think telling it to run those in a subagent should accomplish the same thing and ensure only the answer makes it to the main context. Otherwise you will still have some bloat from reading the exact output, although in some cases that could be good if you’re debugging or something
Not really because it reliably greps or searches the file for relevant info. So far I haven't seen it ever load the whole file. It might be more efficient for the main thread to have a subagent do it but probably at a significant slowdown penalty when all I'm doing is linting or running tests. So this is probably a judgement call depending on the situation.
That's exactly what context-mode does for tool outputs. Instead of dumping raw logs and snapshots into context, it runs them in a sandbox and only returns a summary. The full data stays in a local FTS5 index so you can search it later when you need specifics.
what i want is for the agent to initially get the full data and make the right decision based on it, then later it doesnt need to know as much about how it got there.
isnt that how thinking works? intermediate tokens that then get replaced with the reuslt?
i think something kinda easy for that could be to pretend that pruned output was actually done by a subagent. copy the detailed logs out, and replace it with a compacted summary.
Treat context like git shas. Yes, there is a specific order within a 'branch' but you should be able to do the equivalent of cherry-picking and rebasing it
I didn't really realize how big Gemini was until I saw that Qualia was using it, they apparently used 0.01% of Geminis total tokens (100 billion) in about 3 months, they're in production with the title and escrow industry, so that's a great deal of data going through Gemini, unlike some chat subscription this is all API driven, which I doubt Google is charging at a loss for.
This does not at all tell us Gemini is profitable or driving 15% of its profits. The article does not mention profits even once. It then goes on to bizarrely compare Gemini's monthly active users to Open AI's weekly active ones.
Indeed, that article doesn't support a single part of that claim.
It kinda feels like an LLM-generated article that another LLM picked as a "citation", and then no human bothered to check if it actually said what the LLM said it did.
And, really, advergroup.com? Who sites an advertising agency as if it's a reliable resource?
"AdverGroup Web Design and Creative Media Solutions is a full service advertising agency that delivers digital marketing services. We manage Google Ad Word campaigns and/or Meta Ad Campaigns for local clients in Chicago, Las Vegas and their surrounding suburbs."
So credible a resource on Gemini's performance/profitability... /sarc
But yeah it doesn't even actually say anything about profits, let alone attribute any specific percentage of profits to Gemini. It just vague marketing copy.
reply