Kirill
@kegashin
building stuff. writing about building stuff
540 Following 645 Followers
the RAM shortage has gotten insane
0 GB is an option now, I think
Jev's usage limits once everyone starts using it
finally reading posts from iPhone Duo, feels good
no way. I have 500+ connections on LinkedIn now. Is there a prize or something? What am I supposed to do next?
why does GPT-6 Astra keep leaving tasks unfinished? It does most of the work, but for some reason there's often something left undone
@thsottiaux @OpenAI
I really hope this is as good in practice as it looks on paper
Today, we’re announcing Ternary Bonsai 2 27B.
Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.
Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.
Ternary Bonsai 2 27B is available today under Apache 2.0.
Show more
it's over. so $200 is not enough anymore
there is so much slop in software now. even the big companies keep having outages. there's always some app eating all the RAM on my laptop
while I was writing this, the message queue in my Codex chat just disappeared lol
Show more
just noticed the OpenAI API has a verbosity parameter, but we don't have this parameter in the Codex model picker for some reason. Am I missing something?
idk but seems like a useful option to have
@OpenAI @thsottiaux
Show more
proud member of the $200 club. Sorry, guys, we're not accepting new members
To make sure our current users have an incredible experience and continued access to Astra, we are going to pause subscriptions to our $200 Pro plan. These put the most strain on our systems and we wanted to take the smallest step that allows us to continue giving the broadest access possible. All other plans and the api remain available.
There is no impact to existing accounts and we are working on adding more capacity as fast as we can. Thanks!
Show more
another day, another "we put fly's brain in..." post. guys, can you please put it back in the fly? stop. it has done enough
I'd buy a foldable iPhone Duo, but somehow I need to pay OpenAI $200 a month to make my computer talk to me
is it me or does Codex eat $200 sub's limits like it's $20 one actually
Apple: "...our fastest chip yet..."
Would be funny if it wasn't
why do all the codex extra resets always happen right after my scheduled one? like right the next day or sum
can you check my account next time please?@thsottiaux
helping GPT6 Astra become agi
