Cédric Moreau

[Cédric Moreau @twicedd]

@Tech2Wild Speed (tok/s) is given at which context size?

[Cédric Moreau @twicedd]

@MiaAI_lab @NousResearch Why Hermes particularly?

[Cédric Moreau @twicedd]

@0xSero That’s what I am doing with 2 Mac Studios: GLM 5.2 is super slow (prefill is the biggest problem to me) but it’s ok as a bacground task. I built him a kanban to take tasks and, now, I just added two Sparks to have an adversarial tester challeging what GLM did.

[Cédric Moreau @twicedd]

@TeksEdge I meant for DGX Sparks.

[Cédric Moreau @twicedd]

@TeksEdge Same in Europe, stocks are getting suddently low. The smallest price units (4800€ without taxes) are almost sold out.

[Cédric Moreau @twicedd]

@ivanfioravanti Do you have some temperature numbers?

[Cédric Moreau @twicedd]

@siddharthjthapa @ivanfioravanti I asked my OpenClaw (under GLM 5.2 cloud) to do it on my local EXO (cloned from GitHub) and it just works. Give him the PR.

[Cédric Moreau @twicedd]

@QuietForgee But you get 8bit precision instead of 4bit.

[Cédric Moreau @twicedd]

@ivanfioravanti @pcuenq I was just testing EXO using this PR to patch my local mlx-lm version, seems to work!!! 🔥🔥🔥🔥

[MacLesggy @MacLesggy]

La France, le seul pays « développé » où l’on préfère que des habitants meurent de chaud plutôt que d’installer des Clim’.
#santépublique

[Z.ai @Zai_org]

Introducing GLM-5.2: Frontier Intelligence, Open Weights

- Significant improvements in coding and agentic tasks
- Strong long-horizon capabilities with a 1M context window
- Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong balance between performance and token efficiency
- MIT-licensed open weights
- Same API pricing as GLM-5.1

Tech Blog: https://t.co/LAsxUdN0JZ
Weights: https://t.co/g0A1C4UWx4
API: https://t.co/Kc3E22cbN7
Coding Plan: https://t.co/Nk8Y98HNhU
Chat: https://t.co/WCqWT0qCQb

[Wittgensteino-Aronien🌐 @wittgensteinien]

« Tous les ponts de mai sont passés. Enlevez tous les nuages et remettez le soleil. »

[Ahmad @TheAhmadOsman]

Harness Engineering is the new Software Engineering

[Kimi.ai @Kimi_Moonshot]

Meet Kimi K2.6: Advancing Open-Source Coding

🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2)

What's new:
🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization).
🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D.
🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files.
🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops.
🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop.
-
K2.6 is now live on https://t.co/YutVbwktG0 in chat mode and agent mode.
For production-grade coding, pair K2.6 with Kimi Code: https://t.co/uvoSJKyGCY
-
🔗 API: https://t.co/EOZkbOwCN4
🔗 Tech blog: https://t.co/9wWvgIQSS3
🔗 Weights & code: https://t.co/Be0hjs2RTP

[Cédric Moreau @twicedd]

@ivanfioravanti Mac Studio 512GB, https://t.co/S1btRYj0Q0, https://t.co/nCkzmUAD72

It is closed source software sadly, however it provides efficient KV cache so I feel the "slowness" only once on /new with OpenClaw.

[Cédric Moreau @twicedd]

@Space420613262 @SawyerMerritt @wholemars @kees 4:05 🫣

[Cédric Moreau @twicedd]

@melvynx The closest to me is now Kimi K2.5 on OpenRouter.

[Peter Steinberger 🦞 @steipete]

glad they banned openclaw, the servers are finally reliable again

[Z.ai @Zai_org]

Introducing GLM-5.1: The Next Level of Open Source

- Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo.
- Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations.

Blog: https://t.co/hmyDe4Nel3
Weights: https://t.co/CuUjXcPKJD
API: https://t.co/fz6reja4fb
Coding Plan: https://t.co/Nk8Y98HNhU

Coming to https://t.co/WCqWT0qCQb in the next few days.