Prashant Deva (@pdeva) profile picture

Geek. I like video games and math. Chief guy @ https://teapawt.org/t.co/ZjunoadPpL

San Francisco
Joined April 2007
ported a couple low throughput services from Nodejs to Rust. 97% memory reduction...
3
177
Tried Kagi.. seems they dont refresh their index as fast as Google...
1
116
Apparently OpenAI now blocks Claude from accessing all openai domain pages... Asked Claude to compare OpenAI's approach with Cursor and Anthropic VCS and Claude cannot read it.
We built Pando, a new Git backend for our monorepo, to handle more pushes and fetches without changing how our engineers and agents use Git. Pando cut push latency by ~80% and now serves nearly a petabyte of Git data a day. We can grow Git capacity alongside agent usage.
1
153
seems @OpenAI Dots is being blocked heavily by third parties. Muse is able to do this easily. I feel over time this will extend to Muse too. UPS has already started blocking Muse.
1
1
144
apparently solving Navier Stokes only gets you third spot on HN.. also top comment has nothing to do with solution but around its politics..
76
Replying to @sama
not seeing it in cli. works on the website tho..
1
2
2,950
Replying to @pdeva @thsottiaux
ok found it. apparently you have to explicitly enable it now.. not sure how one is supposed to find/enable ultra mode otherwise.. also Max mode is hidden by default now..
21
did openai just remove Ultra mode from Codex?? I am on Pro subscription btw.. @thsottiaux
1
1
1
131
Replying to @kushxg
seems PR syncing has a bug.. (github is indeed connected, that how it synced the code)
1
216
Origin cant even sync due to Github outage. thats one way to increase github retention metrics..
110