qasim (@clarshio) profile picture

egoless learner. | @stanford cs & inference @BackboardIO

Joined June 2025
Photo by qasim (@clarshio)Photo by qasim (@clarshio)Photo by qasim (@clarshio)Photo by qasim (@clarshio)Photo by qasim (@clarshio)Photo by qasim (@clarshio)Photo by qasim (@clarshio)Photo by qasim (@clarshio)
here's how to bypass cloudflare turnstile/vercel botid/etc gated endpoints. not a lot of people know about this, and i decided i would make a quick tutorial for it. motivation: @thorchh add vercel botid to gate the vote endpoint on hackelo.com. i was really into webscaping & cyber security in middle school, and this brought back a lot of memories. hope people learn something from this!
had some fun 馃構 thanks @thorchh for the dopamine.
2
1
6
1,295
why does @claudeai 's /btw not support images?
24
it's to the point my ai assistant (@interaction) starts telling me to sleep more.
1
4
577
ppl who grew up in the same era, wyd now?
35
who else can only focus when the right song comes on?
26
why aren't people running ads on their resume yet?
36
learning with ai is placebo
1
23
well this is very nice.
1
40
liking coding is newgen now.
35
never forget: your maximum is someone else's minimum.
33
ig they saw my tweet 馃構
i miss poutine 馃様
2
50
here's my secret playbook to effortlessly stay productive at 4am 馃憞 - sing along to taylor swift & disney
1
54
the next robotics frontier is removing stains from clothes. why? because this task 1. has generally very low success rate (even for humans) 2. requires incredible precision in movement and also visual inspection, which generalizes to many different use cases. 3. requires good analysis and thought process, showcasing robot autonomy. the list goes on... i genuinely believe any robotics lab able to solve this will be a unicorn.
1
36
no one in sf knows how to dap properly
1
32
i miss poutine 馃様
1
5
342
codex 馃槶馃槶馃槶馃槶
38
i feel like the problem isnt as simple as routing to the 'best model'. i'm not sure how the recent model fusion models work but, there's so much to account for. for example, if we blindly switch models, we lose the benefits of prompt caching, causing our model routing to be MUCH more expensive at a not equivalent intelligence/speed increase? i could only think of a master-slave relationship (shoutout systems design), where the communication threads are not the same, but more the main model routes a task as a subagent to not break the cache but to get that extra gain... in that case, would it still be considered a 'router' or 'fusion'? or more just harness engineering? i haven't looked too much into it, but perhaps im missing something?
Built a model router with Jev by @typesafeai. Jev decides what model fits your request best and the request is sent to that model.
1
2
101
i am genuinely amazed, wtf
2
2
60
i can't begin to imagine what llms will look like next year.
This is GPT-6 Astra. Anything you can do on a computer, Astra can do for you. Fast.
40