Do you think all the comments in here are positive about the model? Because they aren't. In no way does it seem astroturfed. And yeah, pretty boring to read that kind of comment every time.
Engagement is generally more important than purely positive sentiment.
Anyway these comments were made when this thread was in an earlier state. I agree that it has gone on to be more "organic" looking. That doesn't exclude it initially being manipulated to the top, in my mind, but certainly they aren't carpet-bombing with only booster comments.
Do you dangerously allow permissions? I absolutely cannot use it until they ship an auto approver. As it is now I have it write one bash/python script to do everything it wants to, then I review that. Otherwise it is COMPLETELY unusable and it shocks me when I hear people are using it.
I've used Antigravity as my main coding agent on one of my biggest projects for about a year. It's been great for me. (and I use Claude, Codex, Grok and Muse for all the other projects)
Gemini Flash is a joke for coding. If you can get the same output as you can get with Sol/Astra I'm impressed. Not to mention that Antigravity is awful.
It is not a universal opinion at all that general coding ability has plateaued.
When I have a clean codebase it’s super powerful and faster than I am. Then I start to use it more, more sessions and longer tasks less checking in between.
It kind of works but later I’m in a deadlock where every change introduces new bugs or takes ages. This might be for a lot of reasons for example me going to fast, me losing mental model, me explaining it wrongly.
However when I then start checking the code it’s all spaghetti like frankly the spaghetti Astra produces I’ve never seen before. Processes that should be simple stretch over 11 files with weird wrappers and abstractions and I need a whole day to entangle it.
These are ai assisted user workflows that Im working on in this case.
I just have the feeling no matter what AI just always expands it. And expansions hinders agility and sometimes you need that.
This is incredible! It definitely is better than Suno/Udio and you have quite a lot of creative control over each aspect - plus being able to download the stems is great!
This is incredibly inaccurate. China is why Russia is still even in the war and is still a functioning country. The EU itself supports Russia much more than the US does with its energy imports.
I mean I full source bootstrap deterministic operating systems for secure enclaves from zero. And by from zero, I mean from 180 bytes of human reviewable hex machine code all the way up to a llvm/rust/musl toolchain, custom rust init system, job manager, and a full cryptographic remote attestation stack. Also recently custom bootstrap compilers.
Truly I am not aware of many more complex problems in systems engineering than these, which is why I love working on them, though every new line written is exactly what I would have typed myself when I use LLMs. I mostly use LLMS to help me debug and surgically -delete- dead code and deps to get to results small enough to review in full.
And ~20M tokens a day results in about the max output I can keep up with and carefully review at key checkpoints.
My assumption is the fact my tokens are not unlimited and have ratcheted up one GPU at a time it has caused me to stay much more connected to every line written, but also I am a security engineer working on tech that cannot fail and must be reviewed by a minimum of two humans.
For someone working on video games, I imagine a more lax move fast and break things approach to LLMs might make more sense.
I cannot even comprehend what kind of project could possibly need 3B tokens in a day and still produce results a human could actually hope to review, but do share because I am curious!
That is extremely expensive and not even SOTA level LLMs. Good for you, but you are mistaken in thinking this is the "right" idea for everyone. It gives me a headache just thinking about doing that.
reply