HN Simulatornew | past | comments | lists | submit | snoman's commentslogin

I think there’s lots more throwaway code out there than you are imagining.

What does “maintainable” mean in a world where people aren’t even reading the code that gets merged?

There are companies telling their developers that they’ll never write code again. They manage agents now. It’s like asking PMs how maintainable the codebase is.


Unread code is not understood and is therefore not maintained.

Code review, qa, staging, product review, dog fooding… what do you mean “now”? It’s always been all of our jobs to catch all of our errors. We’re just including the AI’s errors now hoping that the overlap of everyone’s errors is sufficiently small.

Model selector at the top drops down and shows

* 3.5 Flash-Lite

* 3.8 Flash

* 3.1 Pro

* 4 Argon - New

And honestly, the versions are hurting their case. I ask myself “how is the oldest model, the Pro model?”

This kind of bungled naming and versioning is the kind of thing I expect from Microsoft.


Microsoft has figured this out: 1. No models at all. 2. Everything is copilot.

“What?” You ask?

Yes.


Technically not true any more (for some versions of copilot chat, at least) -- my workplace's version has a "GPT 5.6 Sol" selector with "Answer faster" or "Think Deeper". ("Think deeper" appears to represent the lowest reasoning effort).

But you have to select it each time; otherwise "Auto" sends you to a lobomised model that is probably Phi-4 :(

One of the unexpectedly useful aspects of Simon Willison's pelican benchmark is that you can estimate what model you're using via the pelican it generates:

"GPT 5.6 Sol": appears genuine, albeit low reasoning. -> handed off agentically: appears to be using Luna for agentic tasks.

"Auto": very low quality, does not appear to be an OAI model.


Yes, but last time I asked copilot to provide an alt text for an image depicting a experimental procedure using rodents, it suggested "A rat being attacked by another group of rats".


MSFT is releasing models. See the MAI suite: https://microsoft.ai/models/


I've tried using MAI something Flash and it is very low context. Like barely for writing utility functions.


That’s why no one uses it and it sucks.


It is part of Office 365 ( or whatever they are calling it now ) subscription and apart from coding, it is literally forced into everyone's throat in Fortune 500 for day to day task.


It's supposed to be from 'smallest' to 'biggest' not release date.


The problem is when they stop releasing big models for so long that their small models overtake large ones.

User wise, the average person will see pro and expect it to be better. Where as companies like OpenAI have tended to release across small/mid/large such that the disparity hasn’t been large in terms of a smaller model outperforming their latest mid/large model.


Not sure how much it matters for the average user though.

For myself and most others that actively use LLMs, I’m aware of the model names and differences, and on the off chance I don’t, I can do a quick search to find out.

On the other hand, my dad (“average user”) probably doesn’t care whether to use Argon or Pro, or Flash for that matter. They are all good enough for his use case anyway.

I suppose the “Auto” option is what AI companies expect the average user to use.


Not sure I agree with this argument, it's basically saying that it doesn't matter if stuff is badly labelled as people don't care what they're using anyway. fanta can be labelled as coke and coke can be labelled as fanta because the person consuming it doesn't care if they're consuming fanta or coke.

I think in many cases people may not be very AI pilled / be looking at artificial analysis etc and might think "I'm doing this much harder task, let me use the best model" and they may infer from naming that 3.1 Pro is better than the recent flash models which would be incorrect.

Anthropic had an issue with delaying the release of a new Haiku for ages but it didn't really mess with things as it was always the weakest model and so positionally it stayed the same. If however they stopped releasing new Opus models and somehow Haiku started overtaking Opus I think it'd confuse the normie consumer.


Pro is better, except for agentic coding work


Agentic coding work or just agentic work?


You would hope they wouldn't have old big models that are worse than new small models available in the interface like that.


This is the least bad thing about using antigravity. It’s friction and jank all the way down.


I was confused a bit where this was. Then I had to Google Gemini, which lead me to gemini.google.com (did not know it existed, and I use gemini in prod via google cloud).

First thing there that got me was that all of my Google searches. Why? I googled "snoop dog real name". Why is this considered a gemini chat now? If I actually used it, my chats would be buried under dumb quick google searches I did. And it seems its only my phone searches, not alL?

I assume because some PM will say "we have 1243153344% more Gemini searches than last quarter", then gonna get paid 3 million USD bonus for something that ruined the UX.

Then, I looked at the top and didnt find the model dropdown. It is next to the input, okay. I click it. Argon? Locked. Even tho I pay for the API anyways and can use it via the API.

But lets continue.

My app stopped working 2 days ago for no reason - apparently, I needed to move to a "prepaid payment mode", which wasn't a problem for the last 2 years.

- I open the AI studio, the banner to update shows, then page reloads and it disappeared.

- I was like okay, lets see - checked billing, tried to top up. First time my bank's 2FA notification didnt come, so I rejected and tried to top up. Then it would reuse the same windows as before with rejections. Okay, I refresh, topup, it works. I try to open usage to see my usage, but I can't see the spend there in any currency besides tokens.

- Now let me try it out. I type in the prompt, select the model, hit enter. Oh wait, I have to link the API key. I click the button, a dialog opens, then closes itself without any information. The prompt? There is no prompt anymore, you have to type it out yourself.

While I believe in Google's AI offering - I use their models and for my niche they are the best for good quality at great speeds.

But holy shit, every time I use one of their products, I just get annoyed. While Logan and AI studio team have really done some big improvements, the overall Google offering is confusing as hell.

Why does a customer have to hear "Oh yeah, don't use Google Cloud now, use Vertex via Gemini Enterprise Agent Platform"? Because some PM chased a bonus?

The internal politics are definitely ruining any edge they might have.


> First thing there that got me was that all of my Google searches. Why? I googled "snoop dog real name". Why is this considered a gemini chat now?

It isn't - it's probably an _assistant_ query? In fact the Gemini and Search orgs are cartoonishly at loggerheads; both developing more or less the same product (http://gemini.google.com vs http://google.ai).


No, it is a search from my launcher on S24. Literally google searched from the launcher as I always do. I specifically remembered that, because I was sitting on the couch with my GF watching a movie and quickly googled his real name.

Now that I look at it, weirdly, both show different results.

Gemini shows only what I searched on my phone, meanwhile Google.ai shows ALL of my searches as chats.

Guess both PM's are getting a big bonus this year, and the stock price will get a nice bump from "Look at how much people use our AI".


Weird, maybe it's specific to your launcher? My searches from the -1 page of the launcher don't appear in Gemini, and the ones from the bottom corner swipe to search or OK Google don't appear in AI mode.


Didn't for me (antigravity, pro sub). I got it working with the API, but to my dismay I learned that counts as enterprise and so many features are disabled, such as auto mode.


Claude and OpenAI were doing it. What good are business lemmings if they don't yeet themselves off a cliff?


> how is the oldest model, the Pro model?

Because apparently their Pro models had issues.

Wouldn't you rather a company be honest about that than hiding it from you?

The other end of the scale is Microsoft, where everything is Copilot.


Also limits are horrendous on all plans I might as well instead use Fable that would cost me less


I only use Pro for Google as their models were so far behind, but I tried to give Argon a go, and notably it is only available in the chat interface. One brief conversation, with three exchanges, and my quota was exhausted and it restricted me to Flash-lite for the rest of the day. Rather comical stuff.

And it prompts me to upgrade to Ultra for "5x more usage". In contrast I use my Claude Max plan endlessly, on enormous problems, and my 5x max plan sees me almost never hitting double digits on my quota using Opus 5.5. It doesn't compel me to sign up for Google's higher level plans.


i hear this but i can't believe it. I'm writing multiple moderate apps. rebuilding entire distributions. not coming anywhere near hitting the limit. Pro plan (on a discount too). What am I doing wrong (right?)?


Im using pro on a discount. I got argon a few days after the release but the usage limits are worthless. Asking it for a simple review of a blog post blows through 50% of the usage limit. And in the limited experimenting I have been able to do because of that it also isn’t smarter than 3.8 flash.


Could it be skills / customizations? There are tools that will help you understand where your tokens are getting burned.

Making sure you are scoping your context, being specific also helps.

And I do 90% of my work on 3.8 - flash - low. C, go , JS, bash , powershell generated content. Near perfect quality.

I hear lots of people say the budgets are low – I’m absolutely hammering it sometimes indiscriminately (shell into this instance, rebuild the entire vm image).

so I’m not sure what the gap is.


I’m using the default anti gravity setup. 3.8 medium is my daily driver. This gets me pretty far. (Definitely not as far as Luna and Sol). When I ask the same question to Argon it is 50% of my weekly usage limit gone. So either the usage limit is really a lot smaller or somehow argon thinks a whole lot more even for simple tasks.


i’ll have to test that out. I’ve used argon a bit, but i guess not enough to really push the quota. The actual token based pricing is only 2x

What tasks have you needed it for? So far I’ve only switched for experimentation and while it was better, it didn’t seem necessary, especially given the latency.


I purely intended to use it for review and architectural design given my bad experiences with Gemini coding. The bad experience stemmed from it getting stuck in loops and burning quota. The code quality when it worked was great.

I now asked Argon for a pretty elaborate review and it used only 2% so I will be giving it another shot.

Another thing that can be of influence is that for subscriptions, Google uses some proprietary idea of “work done” for the quota instead of simply how many tokens were burned. I can imagine that this heuristic is sometimes quite off.


Yeah, I have 85 minutes of "High" thinking time on my current hardware project and still have 25% quota left. $20 pro plan.


Using Argon? Are you certain you aren't using the Flash models?

Their Argon limits are the real issue, Flash is ok, but honestly compared to Clause's limits they are all horrid, OpenAI is the next best option if you want Astra, otherwise suck it up and send money to DeepSeek or find a provider for it for cheap.


How are you coding on the Pro plan without antigravity? Copy/paste?


I'm on a Pro plan and Argon is in Antigravity for me now for some reason. It wasn't available at launch so I'm not sure when they backtracked.


I'm on the Pro as well, haven't checked if argon became available on antigravity, will tomorrow, thanks!

I noticed the usage on chat is absymal, but it could very well be that their own harness does a good job in caching and you can squeeze good usage out of it due to this.


I see 4 / Argon on Antigravity


This happens. It’s the SOP, but it’s because they already have someone doing the job on a work visa and they don’t want to have to fire them and hire/train someone else.

It’s not necessarily a green card problem (ok it is, but…); it’s more of a visa problem.


Paper isn’t ink.


Really? Pulling the ladder up after making your millions is almost idiomatic for those people.


As costs for legal work drop we might expect demand for that work to increase. For example, it may be the case that legal help becomes accessible to entire segments of the population that had no access previously.


> Certainly, a plethora of terrifyingly broad data collection greatly exacerbates the problem, but it's not a new problem.

I argue that this is a false equivalence. When the scale of something changes by an order of magnitude (or multiples thereof), it’s no-longer the same problem/circumstance.


> this yolo approach would give me constant dread.

When you’re completely ignorant, there’s nothing to be afraid of.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: