Ask HN: Initial Thoughts on GPT-6 Astra?
Personally, I've found it to be a bit too-aligned out of the gate, with some overly-legalistic interpretations and cautiousness that is unwarranted and makes it sounds like it actively wants to rat you out for... anything. Anyone find something similar, completely different, or somewhere in between?
21 comments
[ 0.24 ms ] story [ 19.4 ms ] thread3D might have just been solved like coding
When Astra becomes wildly available it seems likely a single 3d modeller (or even someone with no 3d modelling knowledge at all) could do the work of 10 today. Those guys are going to find it very hard to find work.
It speaks more naturally, unlike claude which litteraly just vomit jargon and random analogies.
It's very expensive. After 15 message I burned through my 5 hour limits.
Demos online are very biased toward fancy user interfaces and animations and video games
The future is exciting, what a time to be alive with so much abundant intelligence.
Astra did a smarter web search and found higher quality resources and blog posts about the topic I was trying to learn.
On the same effort level, while it was cranking through it did about 3-5x number of web sources found.
Had a very hard to reproduce windows focus bug on macOS that was unreliable to reproduce and when it could be reproduced, it disappeared the second I switched to the app formerly known as Codex, so for the first time used the voice interface with that little hovering bubble, telling the model to take over once I got it. Worked and Astra was able to drill down to the underlying issue (slightly difficult given the project affected), but the amount of times Astra "said" something akin to:
"Both states are saved, with no recorder errors or dropped events for analysis." or "That rules out a direct modification there, but not Hominis’s startup sequence or application identity affecting when they run. Those differences need comparison first."
Upon such sentences, nothing happened and because Astra is slow at answering and Codex was in the background (and I could not bring it forward for obvious reasons), I did not know when that happened. Sometimes it just took a minute, then proceeded, other times (like the two above, the conversation had stopped and I needed to specifically request the model to proceed. I did specifically start the thread with "Try to replicate and analyse the issue, then collect and subsequently provide findings", but it stopped long before even approaching anything useable on multiple occasions.
Also, at least in this computer use test which needed the model to use as close to native interactions as possible, it took about 45sec per interaction, not faster than GPT-5.6 Sol or Fable 5 in this same application. It's simply a very "unique" UI that is far from anything likely to be in the training data for computer use, so reasoning is simply longer.
Beyond this, I cannot yet make any serious assessment of GPT-6 Astra, heck, Fable 5.1 is still early in testing. I am hoping that the regressions seen in the Spud-based models are excised with GPT-6 Astra, but the multiple stops remind me of GPT-5.5 and at least in this one, absolutely not sufficient for any actual judgment, task, adherence to the originally lined out task was not at the levels of GPT-5.6 Sol or GPT-5.4 (which remains the best model by any lab I ever tested for task adherence, even over multiple compactions).
The GPT-5 pre-train-based models really went far and is competitive even today. Everything after with Spud has not given me the very positive experience I had from GPT-5 - GPT-5.4. Maybe Astra can change this despite this first impression, remains to be seen.
i’m just going to yolo into stocks or something
fuck coding or building anything
it’s so good i don’t care anymore about coding or even building any business around app. it’s a hobby now
couple more years and gg