Anna retweeted
WTF 😅🚀😳
“98% of Astra’s score at 1.4% of cost”
Cancel the fucking IPOs 😂
We benchmarked DeepSeek V4.1 Flash by @deepseek_ai .
It reached 98% of GPT-6 Astra’s score at 1.4% of the cost on everyday design tasks based on user requests.
Every model except Astra scored lower AND cost more.
Are open models overtaking closed ones?
Full results below ↘️
When major LLM providers go down at the same time, it is rarely a coincidence. It usually points to a shared dependency in the infrastructure layer or a massive routing issue at the CDN level.
news.ycombinator.com/item?id…
Anna retweeted
pros:
- works with your claude subs
- works with your codex subs
- open source
- works remotely (`npx t3 connect`)
- great mobile app
- inbox-style sidebar
- incredible performance
cons:
- associated with theo
Anna retweeted
Getting Started with Grok Bot
01:00 What is @Bot?
05:26 Anatomy of a bot
08:49 3 ways to run
12:04 Multi-bot chains
16:06 Workflow 1: X followers to @Notion
20:29 Workflow 2: Personal software
23:08 Workflow 3: Coding with @cursor_ai
26:44 Workflow 4: Search
28:27 Recap
Getting Started with Grok Bot
A walkthrough of Grok Bot, an agent that runs on a persistent Linux VM in the cloud and can use a computer the same way you do.
Talking to Grokbot feels less like talking to a bot and more like texting a friend who had 7 espressos and read Wikipedia’s entire database at 3 AM
Anna retweeted
OX Alpha is hosted in America!! 🇺🇸
I sent 49 identical one-token requests from 7 Cloudflare regions, rotated the order to control for load and matched every response to OpenRouter’s per-generation server timing.
This isolated the geographic network floor:
ATL: 57 ms
DFW: 76 ms
Europe: 125–132 ms
Asia: 202–340 ms
Australia: 279 ms
A robust 6-of-7 fit converged at 43°N, 73°W, with the plausible band covering the US East Coast into southeastern Canada.
Best interpretation: OX Alpha’s serving path is anchored in eastern North America, most likely US East.
The only potential remaining caveat: this could be @OpenRouter backend handoff rather than the physical GPU rack.


















