moshegramovsky

The biggest mistake of Joe Biden's life was not making sure that Trump was in handcuffs on the afternoon of January 20th, 2021.

This is 100% absolutely my experience as well. Especially the needless abstractions and endless rounds of corrections. That was literally my entire last week of work.

I work on a very large code base (millions of LOC) and I've had lackluster results with autonomous work and 1 shotting. AI is definitely fantastic at working on many programming problems but I am not seeing amazing results at refactoring. In fact, I am seeing very poor results, even with Astra, even with extensive planning docs. All the recent models I've used can definitely get that refactor done, but not autonomously. It needs to be small slices. I've yet to see it 1 shot anything really complicated.

Here's a good example with some assumptions on my part: I work in C++ and it really feels like the models are trained so hard to keep everything compiling all the time. That's a huge negative in my opinion because what happens is that the AI will do things like use wrappers to keep things compiling, even when that basically results in creating or hiding abstraction leaks. Or they get sneaky and include a header they shouldn't. Or they actually do see that there should be a layer boundary and they write some kind of abstraction to cross it but the abstraction itself is garbage or doesn't follow existing API patterns. The AI could invent 10 different, new patterns when there is already 1 existing pattern they should use.

I feel like a lot of this involves a lot of babysitting prompts. Not that there's anything wrong with that of course.

100% hard agree.

I used about 10 hours of Astra high-thinking compute time and it was a bad experience. Incredibly slow (prompts running for 30/40 minutes) to do simple things. As a result, Astra didn't get much done. It needs the same small implementation slices as GPT 5.5/others, but was much slower and didn't generate better results. (On a complex infra project/across a large codebase.)

It was absolutely terrible on a few long running tasks (~2 hours each). It really doesn't seem to be better than 5.5 at most programming jobs.

I'm on a $200 per month plan with OpenAI, which I am happy with and is definitely worth it. But I also use Google Gemini a lot (paid plan) and it is incredibly fast. Like I can't get coffee fast. Like I can't send an email fast.

OpenAI is making some excellent products for sure but I'm not going to keep using Astra unless I can get some benefit from it. It really seems like even the frontier models just aren't good at working autonomously on large codebase situations. Just because something compiles doesn't make it right!! In one of those 2 hour implementations, Astra engaged in *fucking EPIC cheating*. It wrote a probe/side app and then worked through the design there. Um, what? Not that it's invalid to do this but I actually have to test in the live codebase or I can't possibly say that something is working.

Just because you can, doesn't mean you should.

This product has the classic problem of being a feature that's being turned into a product. I don't think this can survive on its own.

100% this.

I was a huge Gemini fan, and I think the model itself is still very good. But Antigravity is absolutely horrible. It routinely writes broken code and then ends up in a short term cycle of reverting and re-implementing.

It's so bad that I don't use it for writing code and certainly wouldn't even bother trying to get it to refactor anything. It's been relegated it to analysis and planning. It is excellent there.

I can't be the only one who find this a little inexplicable that a company with Google's resources is fumbling this so badly.

I have mostly enjoyed AI programming and I do like using Codex. The truth is that it sometimes makes me more way more productive, but not usually. Many days are spent writing specs and babysitting prompts and it can suck. Even expensive Codex 5.4/5.5 with high thinking writes code that is just ... lazy. It takes a lot of work to get it to write excellent code. It's definitely a full time job all by itself.

I'm not talking about rocket scientist code either - I'm talking about things using raw for( instead of range-based for, or writing code that is absolutely fucking riddled with imperative logic, hacks, and kludges, when something should clearly be data-driven. Stuff that is so bad I have to tell it to start over. It routinely designs amazing architecture and absolute shit architecture, sometimes on the same day. It's just so weirdly inconsistent. If you ask it to fix a bug then you have to double check if it used a hack and sometimes it will admit to it. Sometimes it lies.

I just do not see how AI is going to replace large numbers of seasoned engineers. That would be a disaster for companies that try it. Could it replace large numbers of juniors? Yes. And maybe I am being fantastically naive. I'm 100% willing to concede that it's possible or even likely.

I've criticized Antigravity in this same conversation, but Google Gemini is good at coding. Even Flash 3.5 low is good at coding. The problem is that Google isn't hungry anymore and it really really really shows in how much they've botched everything to do with Antigravity.

Facebook is ethically challenged and that's putting it very very very mildly. Yes, they have unlimited money, but at a certain point, it comes across like a rich dude at a bar telling a beautiful woman that he'll buy her a diamond bracelet if she will just come over to his place right now. They make my skin crawl.

I am a huge fan of Google Gemini, but Antigravity is not a good product. Just recently I've had issues with:

* Repeated instances of incorrect code insertion that the agent cannot clean up. Sure, version control, but this is often happening in new files that aren't even in version control yet.

* Lost chat history when I close and restart the app.

* Not being able to restore a chat from the history (just saw this last week).

* Overly broad searches that waste time and tokens.

* No vertical scroll bar arrows. WTF?? Doesn't the interface look "flat" enough already? This feels arbitrary and stupid.

* The previous chat prompt takes up a large portion of the vertical space of the chat window, even on a high res display.

When it works Antigravity is excellent. When it doesn't work, it's absolutely horrible. If you check the update history, there are usually just a few items and they're super generic things like "Fixed a bug with text entry.".

I don't see it improving at any kind of reasonable pace, even over the last 6 months As a result, I've mostly relegated Antigravity to a planning tool and it does an excellent job. Or I use it to write prompts that I give to Codex. It definitely can do an excellent job writing code sometimes, but sometimes it also does an absolutely horrible job with not breaking the code when it inserts it. It seems to be terrible at understanding C++ braces. How often? Way too often. I always know it's happening because it prompts me to run Git while it's doing something. LOL, that's how I know that it's broken something.

Codex is definitely way, way, way better. It's not even a contest at this point. Codex never breaks my code. It might not always do what I want, but it's just an order of magnitude better than Antigravity. Antigravity really feels like a comedy of errors at this point. ESPECIALLY from a company with Google's resources.

Hannah Arendt wrote about the collapse of shared truth in societies. Trump is in some terrible company, literally and figuratively.

It isn't any different. Hypocrisy, along with greed, is ruining the world.

Unfortunately, you are 100% correct. Trump was never going to deliver because he's the living, breathing embodiment of two things: Dunning-Kruger, and the ethos of disgusting corporate greed/abuse that's ruining the country. Trump and people like him are the most dangerous anti-democratic force ever assembled in America.

Right but you act like nothing can be done about that. If you outsource enough then don't count on the US government to protect you overseas. Go ahead and risk nationalization. The very fact that we are having this discussion shows how bad the situation is: companies can effectively threaten to move all their jobs overseas, thereby threatening US workers with economic ruin. That's not okay.

The government grants broad liability shields to owners of companies because there is a vested state interest in facilitating commerce/economic growth. I guess if companies are just going to move overseas then maybe those liability shields could just be vacated. They don't deserve to have their cake and eat it too. It's easy: want the liability shield? Stop being fucking greedy and be a good corporate citizen. Otherwise, no cake for you.

Did you write a patronizing comment because you don't have an intellectual argument? Making comments about an abusive visa program isn't crying. Nowhere have I said immigrants are to blame, nor have I said that we should stop immigration.

The H-1B visa program is simply another element of the system that capital uses to abuse labor in the United States. It's not enough that healthcare (if you are even lucky enough to get any) is tied to employment. The low bar for bringing in foreign workers is used as a negotiating tactic by employers. There is no equivalent leverage for workers, absent economic ruin. This problem affects tens of millions of Americans and that's not normal and it's not okay. Maybe the law should allow H-1B visa, but also charge an absolutely huge premium (> $250k) that the company commits to worker healthcare or something. If the positions are so essential then $250k is still an incredibly good deal.

America has to start addressing the imbalance of power between capital and labor. It's gotten bad enough that one could easily argue that it's becoming a potent anti-democratic force in the US. And, I'm sorry, but Americans should not have to cede their desire for equal economic footing because people like you want intimate that it's about "not hiring immigrants".

You're definitely not wrong but I still voted for Kamala because I didn't want Trump to burn the country down.

That's MAGA for you. They're not even complaining (very much) about super high gas prices. They absolutely excoriated Biden when the price went up even a nickel. MAGA will sacrifice absolutely anything for their king.

I appreciate the information. However, labor Arbitrage affects millions of American workers. It probably affects tens of millions. I just cannot fathom that companies today have any positive ethical reasons for wanting to participate. It gives them another stick to use against both groups of workers. Also, H-1B was started in 1990, so well after World War II.

I work in Bellevue, WA, and there are a lot of Indians. How many are on H-1B? I I don't know. Anyway, I am a life long Democrat, but the Democratic Party needs to do something huge for American workers (like single payer healthcare) or we'll have Trump III or its equivalent or worse than that.

H-1B exists to make unfathomably rich corporations and people even more unfathomably rich. That's the only reason. That's why we don't have single payer. How can corporations function if employees don't equate job loss with total economic and social ruin?

By taxes, do you mean buying Trump's crypto?

I don't understand why American workers would support this program at this scale. Furthermore, I believe universities and other similar researchy/affiliated non-profits are exempt from the hiring caps.

I just cannot imagine executives at tech companies/body shops having any positive ethical motivations. More like "they'll do what we say without complaining or they'll go home". There's no way it's not just a hugely abusive to both pools of workers. The whole thing really feels like another example of the imbalance between labor and capital in the US.

Who originally wanted H-1B/etc? Rich people with money and power? Of course!

I heard it's because she wouldn't settle his 10 billion lawsuit grift.

You don't have to shop at Amazon. I know I don't. Anymore.

> I still use them but find that more of the time is spent arguing with it and correcting problems with it than actually getting any useful product.

I feel the same. They're better at some things yes, but also worse at other things. And for me, they're worse at my really important use cases. I could spend a month typing prompts into Codex or AntiGravity and still be left holding the bag. Just yesterday I had a fresh prompt and Geminin bombed super hard on some basic work. Insisting the problem was X when it wasn't. I don't know. I was super bullish but now I'm feeling far from sold on it.

> If you ask people (who are not doctors) to remember this time they will likely tell you this is what they remember. I also do have tons of anecdotal accounts of doctors saying the Covid 19 vaccine is safe and you can find many yourself by searching. Here’s one: https://fb.watch/Evzwfkc6Mp/?mibextid=wwXIfr

> No it’s not false. Most of the writing on human medical stuff is scientific in nature. Formalized with experimental trials which is the strongest form of truth humanity has both practically and theoretically. This “medical science” is even more accurate than other black box sciences like psychology as clinical trials have ultra high thresholds and even test for causality (in contrast to much of science only covers correlation and assumes causality through probabilistic reasoning)

Sorry, but these kinds of remarks wreck your credibility and make it impossible for me to take you seriously.

> There are 800000k patients who die or are seriously injured by a misdiagnosis every year.

Yes, I once sat in a recovery room with my Mom after she had been given too much propofol during an endoscopy. Despite the fact that her breathing was labored, the clinic she was at didn't want to do anything so I called 911. I'm not sure what happened, but I can see that side of your point. I did learn to be much more careful about how I saw to my parents medical care after that.

I cleaned it up with an LLM. Is there a problem with that?

Sorry, I should be clear: do you have a problem with that?

This definitely matches my experience.

Gemini 2.5 was genuinely impressive. I even talked it up here. I was a proper fanboy and really enjoyed using it. Gemini 3 is still good at certain things, but it is clearly worse than 2.5 when it comes to working with larger codebases. Recently, I was using AntiGravity and it could not help me find or fix a reference-counting bug. ( 50 classes, 20k LOC total, so well within context limits ) I know AntiGravity is new, which explains why it is rough around the edges. But it is built on Gemini, so the results should at least be on par with Gemini 3, right? Apparently not. I am an excellent prompter, and no amount of additional context, call stacks, watch-window values, you name it, made any difference.

I still use Gemini for code reviews and simple problems, and it remains excellent for those use cases. But in many respects, Gemini 3 is a regression. It hallucinates more, listens less, and seems oddly resistant to evidence. It produces lots of lofty, confident-sounding statements while ignoring the actual facts in front of it. The experience can be exhausting, and I find myself using it much less as a result. I guess this is typical of companies these days - do something great and then enshittify it? Or maybe there are technical issues I'm not aware of.

What is especially interesting is reading all the articles proclaiming how incredible AI coding has become. And to be fair, it is impressive, but it is nowhere near a magic bullet. I recently saw a non-programmer designer type claiming he no longer needs developers. Good luck with that. Have fun debugging a memory leak, untangling a database issue, or maintaining a non-trivial codebase.

At this point, I am pretty sure my use cases are going to scale inversely with my patience and with my growing disappointment.

> The proper decorum here is if the doctor made the wrong diagnosis. All fees and causal charges made by the doctor must be fully refunded and paid for. It’s only fair given the premium they were originally given to make a false diagnosis.

Do you think it would be better to live in a world with no doctors? You can already live in that world if you want. Thanks to doctors, millions of people around the world no longer die from treatable illnesses. Everyone in my family has either had their life saved, or saved from ruin, by a doctor at one point or another.