cool work folks – nice to see SDPO explored in practical/async setups!
SYSTEMS
-
GLM endpoint slow, mistakes help understanding, coding product fine
By
–
Yesterday evening GLM endpoint was slow, high traffic during U.S. working hours. Today it's making seemingly sillier mistakes, but every one it makes helps me understand the solution better — which has its benefits. Not perfect, but the subfrontier coding product is fine as-is.
-
BIGSET: A New Standard in AI Architecture, Beyond Simple Wrappers
By
–
But before we dive in, I have to say: BIGSET goes far beyond a simple wrapper. The tech sets a new standard for AI architecture: → AI infers the schema automatically
→ Sub-agents work in parallel
→ Source tracking per row
→ Exports to CSV/XLSX and more! keep scrolling ↓ -
Perplexity’s New Agent Architecture: Python, Sandbox, and Efficiency Gains
By
–
Perplexity stopped treating search as one API call. Its agents now write Python that fans out queries, filters results, and joins evidence in a sandbox. On a 200+ CVE task: 100% accuracy, 85.1% fewer tokens. The SDK is private. The pattern isn't, so lets use it with Hermes?
-
Hallo-Live: Real-Time Joint Audio-Video Avatar Generation
By
–
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation Paper: https://
arxiv.org/abs/2604.23632
Code: https://
github.com/fudan-generati
ve-vision/Hallo-Live
… Our report: https://
mp.weixin.qq.com/s/LCgg_MzjSHqv
YxPIOIhZIw
… #PapersAccepted by Jiqizhixin -
Hallo-Live: streaming audio-video avatar generation from Fudan & Baidu
By
–
What if your avatar could talk and move in real time?
— 机器之心 JIQIZHIXIN (@jiqizhixin) 3 juin 2026
Fudan & Baidu present Hallo-Live: streaming audio-video avatar generation.
Dual-stream diffusion + future-expanding attention syncs lips to upcoming speech.
Human-preference distillation preserves quality. 20 FPS, 0.94s… pic.twitter.com/0GHiOm5h2xWhat if your avatar could talk and move in real time? Fudan & Baidu present Hallo-Live: streaming audio-video avatar generation. Dual-stream diffusion + future-expanding attention syncs lips to upcoming speech. Human-preference distillation preserves quality. 20 FPS, 0.94s
-
New Codex plugins turn it into role specialists instantly
By
–
We’re making Codex more useful for your work by expanding plugins beyond individual tools. These plugins turn Codex into a specialist for a specific role with a single install, no coding required. Codex can access 62 popular apps and 110 skills for work across sales, data
-
Agent labs need internal and external routers, congrats matanSF
By
–
imo every agent lab needs to also build a router internally/externally. no two ways about it. grats to @matanSF for getting there
-
Full-load GPU limited to 220W with DFlash, DDTree optimizations
By
–
Looks like this under full-load btw Lots of juice to squeeze yet with DFlash / DDTree / Spec. Decoding / etc Also, power limiting the GPUs to 220w down from 440w as well (okay w/ leaving the perf. loss on the table given the heat / energy savings from that)
-
14 RTX 3090s running 42 parallel agents at full 256k context
By
–
14x RTX 3090s + Qwen 3.6 27B Running 42 agents IN PARALLEL at full 256k context – exl3 6bpw
– fp8 KV Cache
– Aphrodite Inference Engine w/ tp=2, pp=7 The world of agents will run locally btw