Andrei 𒅴𒂠

Reality and love are almost contradictory for me. It's funny, every one of my exs are now married. Men go out with me, we break up and then they get married. Later they call me to thank me for teaching them what love is, that I taught them to care and respect women. - Celine

trying to get --enable-dp-attention too, was crashing with deepseek and EAGLE

using sglang python -m sglang.launch_server --host 0.0.0.0 --port 8000 --model-path deepseek-ai/DeepSeek-V4-Flash --tp-size 4 --dp-size 2 --config /root/config.yaml --enable-mixed-chunk yaml config (config_deepseek_v4.yaml): host: 0.0.0.0 log-level: info tool-call-parser: deepseekv4 reasoning-parser: deepseek-v4 trust-remote-code: true # Memory mem-fraction-static: 0.92 context-length: 1048576 # 1M chunked-prefill-size: 8192 # MoE moe-runner-backend: flashinfer_mxfp4 # Observability enable-metrics: true enable-cache-report: true # Batching — 8x B200 max-running-requests: 64 cuda-graph-max-bs: 128 # EAGLE 3/1/4 speculative decoding speculative-algorithm: EAGLE speculative-num-steps: 3 speculative-eagle-topk: 1 speculative-num-draft-tokens: 4 # Scheduling schedule-policy: lpm num-continuous-decode-steps: 4 # Kernel fusions enable-mixed-chunk: true enable-fused-qk-norm-rope: true disable-flashinfer-autotune: true env vars (in modal container): SGLANG_ENABLE_SPEC_V2=1 SGLANG_ENABLE_THINKING=1 SGLANG_JIT_DEEPGEMM_PRECOMPILE=0 HF_HOME=/cache/huggingface HF_XET_HIGH_PERFORMANCE=1 HF_HUB_ENABLE_HF_TRANSFER=1

started self-hosting models, my Arrakis, my Dune deepseek-v4-flash on modal 8xB200 180 TPS

benchmaxxed

3.1 pro is utterly horrible for any agentic use case and everyone knows it

@sebisemeniuc top

@andreidro opus-4-7 only

anara mogging - last 7 days bro

@sebisemeniuc what models

@andreidro 🫡 tokenmaxxing

I made a game where Sam Altman calls your pitch "pre-seed energy" and Peter Thiel offers you a term sheet AI rewrites the whole story every play, pulled from real SF news and stories built in couple of days for #ElevenHacks @elevenlabs and @zeddotdev hack #6

@BogdanGruiaIvan we goon now

🇷🇴 Romania enters the big league of AI. We’ve launched the EOI to select the consortium leader for the Black Sea AI Gigafactory, starting with 20,000 GPUs, scalable to 100,000+. We’re seeking a strong, experienced partner. Apply by June 14, 2026, here: bit.ly/4cug5IH

I really liked wispr flow but didn’t feel like paying $12/month for it, so i built a local-only open source version it’s a native macos dictation app that runs whisper fully on-device and types directly into any app if you use dictation, this is a simple alternative that just works, fully local you can download the dmg and use it right away

new tattoo frfr

@octavicristea i like the colour in last one, but is hard to read, would try a mesh gradient over the image on the text side

which one do you guys think is the best?

@octavicristea top

i built a tool that lets AI agents explore the web like a human would give it a URL and watch it go. it scrapes the page, previews every link, picks where to go next, and the whole thing plays out as a live graph open source. here's what it looks like:

@octavicristea clawing on phone fr

why does the most popular open-source project in GitHub history require a CS degree to set up? that's the question I couldn't stop thinking about. so I built the answer. Clapp AI is OpenClaw for your phone. download, sign in, agent ready. no terminal, no Docker, no Mac Mini. tell it "send me a morning email digest at 8am." tell it "post to my socials at noon." it does it. Gmail, Slack, GitHub, Calendar, Notion, Instagram, 10,000+ integrations, not demos. iOS now. Android coming soon.

Claude vs OpenAI

please uwu github.com/vercel/ai/pull…

an idea for sending custom approval data in AI SDK

@ctatedev - Added background launch guidance (open -g -a "Slack" --args --remote-debugging-port=9222) opening in background helps with that

@ctatedev asking to edit message with slack in background is really messy rn

The "holy shit" moment when I realized agent-browser can control Slack npx skills add vercel-labs/agent-browser --skill slack