piyh
piyh on Hacker News
>we paused certain frontier training (including certain training for Astra) for two weeks
So the pause wasn't really a pause, got it
do you really think that a less negligent anthropic/oai/meta would really fair better against future models?
The Legend of Korra come to life
Wouldn't you want to keep this for internal development? Keep the single thread gains for yourself.
Your own link says:
In / Out Price
$0.289 / $2.40per 1M
Qwen 3.6 is ~$2/m tok, 3.8 should be drop in replacement. Gemma 31B is $0.34/m tok. The price differential on these models is massive on openrouter.
Feels like the 90's again where single threaded speed is improving fast. ASICs and wafer scale rather than node shrinks, but end result to me the consumer feels the same.
Sol on Cerebras is going to be expensive AF
That SWEBench drop going from bf16 to fp4 is massive
SSD NAND reads are nearly infinite. Still makes me uncomfortable, but writing is what kills. There's a reason SSDs are rated by TBW, not TBR.
Rendering 3d worlds has hugely improved though.
Gemma E2B QAT will run on a 4 gig RAM pi.
Early days or not, Google fucking deleted my IDE and wiped my settings. It took them days to roll out a fix, by which point I had migrated off Antigravity.
>As a software developer
My man has written too many JIRA story descriptions
Posted by
piyh on Sunday July 12, 2026 @12:49AM
from the medium.com dept.
I tried running any model on my 1070 and it instantly crashes my old tower, probably time to get off windows and run linux on it.
The only thing I remember about CORS is that it takes way longer than expected to debug, by design the error messages sent to the browser are intentionally gutted, and CORS error scenarios are hard to tell from other failure modes atfirst glance.
I was asking nano banana to modify pictures of me to reflect if I dressed or wore my hair differently.
It ended up inserting alien hands touching my hair with smooth pale skin holding weird wormy things.
Every once in awhile you get a peek of the Eldritch horror lurking below our helpful assistants
TBF, Flash 3.5 was released 2 days ago
They nuked anti-gravity and installed their codex knockoff in place. The vs code fork IDE and all your settings with it have been removed. Reinstalling the anti-gravity IDE, as it's been renamed does not bring back any of your settings or extensions.
This is a cluster across the entire product line
9 different frameworks being pushed in the comments of this thread. 2026 truly is the year of agents.
Are you using haiku for most tasks? I'm in the Google ecosystem so I'm curious how it is on the other side.
JavaScript living only as a built artifact in an s3 bucket makes for a much simpler life.
Trade volume and buying API credits are very dissimilar ways of measuring value. One can be wash traded into oblivion, the other is burning a hole in corporate accounts.
I use a quota monitor and grind out code on Gemini 3 flash. Only go to sonnet or pro is there's issues flash can't deal with or I have a critical architecture I need nailed on the first try.
I still review every line generated.
Gemini 3.1 pro on the web interface still works if my problems are scoped to a single module or two and my better model quotas are exhausted in the IDE.
For $7 over what I was already paying for storage, primarily using flash is still a good development experience for me.
Already paying for Google photo storage, AI pro for an extra $7 is a steal with anti-gravity.
No idea, I googled "cache busting in vite" and it was by far the most comprehensive result.
Posted by
piyh on Saturday April 04, 2026 @09:19PM
from the self-post dept.
Is there any prior writing about finding under-sampled latent space in a model and directing that behavior into documentation writing?I was fixing cache invalidation and this page was the right thing at the right time to help me understand the solution to the problem: https://grokipedia.com/page/Cache_busting_in_Vite#troubleshootingAFAIK, that collection of information is a new synthesis of...