seclee @seclee3

Phd student@SDU | CloudNative, Network, LLMs, GPU system | #seclee seclee.com Joined November 2021

Tweets

52
Followers

7
Following

220
Likes

251

seclee @seclee3

2 months ago

@deepseek_ai @OpenAI @opencode with DeepSeek V4, no special adaptation needed, compatibility is seamless. This model is way smarter than Qwen3.6.

0 0 0 60 0

View Details

Just tested DeepSeek V4 Pro + OpenCode, already better than 5.3-Codex in engineering design, performance advice, and code quality. High KV cache hit rate also cuts costs significantly. @deepseek_ai @OpenAI

1 0 0 71 0

View Details

seclee @seclee3

3 months ago

@cyodyssey @BNBCHAIN 111

0 0 0 19 0

View Details

Ishan @ishanspatil

3 months ago

There's an underrated part of the AI Sat Mini design that nobody seems to have picked up on. Up until now, the 2 major critiques to Orbital Datacenters have fundamentally been: 1. The Solar Irradiance hitting the satellite in a Dawn-Dusk SSO will make running GPUs on it thermally impractical 2. The Earth Albedo hitting the radiators will make it challenging to dissipate heat The AI Sat Mini config takes care of both. - The Flatsat Bus is pointed perpendicular to the sun load edge-first, minimizing Solar Load. - The Radiator is pointed perpendicular to both the Earth and the Sun Loads, able to dissipate heat to free space on both sides - The Solar Array mounting seems to be fairly thermally isolated, and the massive span allows for a ton of radiative dissipation from the dark rear-face (as is often the case with space SPAs, they don't store that much) These are fairly clever orbit & conops driven geometry choices that become apparent once you start mission design, and de-constrain the design quite simply. Your flatellite + radiator is almost permanently shaded, and the only incentive becomes to run your compute as hot as possible to leverage the Eb = σ• T⁴ scaling. Passive heatpipes conducting heat from the chip pedestal to the radiator may be sufficient, without engaging in the insane exercise of mass producing 0g coolant pumps. Now there seem to be 2 variants here between the images posted, but that may just be render inaccuracy. Vertical Config: Image 1 (with the Starship for scale) shows the solar arrays along the edge of the flatellite. Horizontal Config: Image 4 (the on-orbit render) shows the solar arrays perpendicular to the face of the flatellite. Either scenario supports the earlier observations, as the solar array plane is free to rotate. However as others have noted, the Vertical config may offer a fair degree of gravity gradient stabilization. This is another interesting bit - Orbital Compute will require very little pointing accuracy, compared to most other space applications like EO or Comms that track a target (Imaging AOI or Receivers). As long as the satellite points roughly at the sun, and the gimbaled ISL terminals can maintain a stable connection to Starlink, the pointing requirement is negligibly coarse. You could probably forgo reaction wheels and control this whole thing with magnetorquer pulses. SpaceX has a habit of eliminating broad constraints at architecture level quite cleverly, and I was looking forward to how they think about Orbital Compute. Safe to say I was quite delighted by this design.

Steve Jurvetson @FutureJurvetson

3 months ago

First view of the 100kw AI Mini Sat with solar panels and heat radiator to scale. “And that’s just the Mini version. We expect future versions to go to the megawatt range.” — Elon The key missing ingredient is a terawatt of AI compute. Fully integrated fab with recursive

230 670 6K 21.7M 882

8 6 142 27K 72

View Details

seclee @seclee3

3 months ago

@zhang_benita 挑战成功，断断续续听了三天

0 0 0 43 0

View Details

seclee @seclee3

3 months ago

@sanchitmonga22 yep!

0 0 0 13 0

View Details

seclee @seclee3

4 months ago

ModelGate An OpenAI-compatible API Gateway for local LLM deployment. Multi-backend. Quota control. Rate limiting. Hybrid routing. Open source ↓ github.com/derekwin/Model…

2 0 0 34 0

View Details

seclee @seclee3

4 months ago

8/ 📉 Log noise reduction: Info level now focuses on exceptions only for cleaner logs and better debugging.

0 0 0 15 0

View Details

seclee @seclee3

4 months ago

7/ 💡 Quota deduction is now atomic to prevent over-deductions—more precise control. ✅

1 0 0 16 0

View Details

seclee @seclee3

4 months ago

1/ 🚀 Merged 7 small PRs into ModelGate today! Major improvements on security, stability, and maintainability. Let's dive in! 🎉 #Go #LLM #APIGateway #OpenSource

1 0 0 25 0

View Details

seclee @seclee3

4 months ago

Local LLMs are easy. Production LLM infrastructure is not. If you’re serious about AI infra, you need a model-aware gateway layer. Open source ↓ github.com/derekwin/Model… Would love feedback from infra builders.

0 0 0 22 0

View Details

seclee @seclee3

4 months ago

This unlocks 3 powerful patterns: 1️⃣ Enterprise internal AI governance 2️⃣ SaaS tiered AI monetization 3️⃣ Vertical model API productization Without rebuilding auth + billing every time.

1 0 0 13 0

View Details

seclee @seclee3

4 months ago

Most people think running a local LLM = docker run ollama. That’s cute. Running it in production — with multiple users, quotas, routing, and hybrid cloud — is a completely different architecture problem. Let’s break it down 👇