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.
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.
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.
While being slow to pass judgment or disregard an approach is a valuable trait in a senior Eng, I think 3 years is plenty of time to wait for proof of concept to pan out. It’s not panning out, it doesn’t seem on the verge of panning out, and soon the real cost is going to be passed on and the subsidies will end. LLMs see ripe to be the new IDEs, but not the new Engineers
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.
reply