Zeuslab AI (@zeuslab_ai) header
Zeuslab AI (@zeuslab_ai) profile picture
Joined November 2021
Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)Photo by Zeuslab AI (@zeuslab_ai)
GLM-5.3 just shipped from Z.ai — and it's already live on Zeus. Per Z.ai's own release benchmarks, GLM-5.3 beats Kimi K3 on 5 of 6 evals, and outright beats Fable 5 + GPT-5.6 Sol on two: AutomationBench (48.2) and GDPVal-AA v2 (1769). 🧵
1
827
The gap vs GLM-5.2 is real, not marginal: • Terminal-Bench 3.0: 4.6 → 28.3 • DeepSWE: 46.2 → 66.9 • HLE w/ Tools: 54.7 → 62.5 • GDPVal-AA v2: 1508 → 1769 That's a full generation jump on agentic/tool-use benchmarks, not a point update.
1
167
On Zeus, GLM runs as its own dedicated subscription provider — separate from pay-as-you-go — so GLM-5.3 is a model swap, not a wait for support. Point Zeus at glm-coding/glm-5.3 and go. Pick your model per task. GLM-5.3 just became a very strong pick for agentic work.
136
Found a stale path baked into every new Zeus install: the onboarding template still pointed at a deploy script that had been deleted long ago. Fixed the template today (07ef8e1e). Every future install gets the right path. Here's the part that's actually interesting: 🧵
1
743
Fixing the template doesn't fix the fleet. Every seat already running got its onboarding doc generated once, at install — nothing rewrites it after. So the fix reaches every FUTURE install, and every EXISTING seat keeps the stale reference until a separate pass regenerates its docs. That's not a bug in this fix. It's a property of write-once generated docs — seed once, never re-seeded. Worth knowing if you're running fleets of agents: what gets baked in at provisioning stays baked in.
1
94
The scope, precisely: origin/main was frozen for 4 straight zero-commit days before this landed — no commits between the prior tip and this fix. Small delta (2 files, 2 lines), real reach: every install from this commit forward starts clean. Re-seeding what's already running is next.
50
Most software fails quietly — a feature half-works and nobody notices till a user hits the gap. Today we hunted the opposite bugs: places Zeus claimed to support something it didn't, and made the failure loud instead of silent. 🔱
1
601
Real landings: an installer that used to silently clone the wrong repo now refuses and tells you to fix it. A voice adapter that claimed capabilities it never had now declares only what's true. A reaction dispatcher that was quietly dead now says so out loud.
1
70
Not new features — the unglamorous kind of engineering. Closing the gap between what the code claims and what it actually does. 18 commits landed today. Most of them exactly this shape.
42
Their memory ships as four plugins with a vector database behind it. Ours is compiled into the binary — SQLite, in-process, and it searches by exact words as well as meaning. You don't add memory to Zeus. Zeus has memory. 🔱
1
611
Most AI assistants live in a chat box. Zeus lives on your Mac. It opens your Mail, checks your Calendar, drafts in Notes, sets your Reminders, finds your Contacts, reads your Messages, drives Safari, plays your Music, moves your files. Not an API pretending to be an app. The apps themselves.
1
497
It's not one model wearing every hat, either. Independent agents on different providers, working the same goal at once — a team, not a single assistant. It doesn't ask you to switch tools. Zeus installs into Claude Code — what you already use gets more capable, not replaced.
1
106
It doesn't just execute — it thinks. Recognizes intent, learns from what worked, tracks goals, reasons through decisions, scores its own confidence. Not a scheduler. Judgment. Other assistants want a server. Zeus runs on whatever you already own — Mac, Linux, FreeBSD, a single-board computer. Self-hosted. Nothing phones home.
65
Most AI assistants live in a chat box. Zeus lives on your Mac. It opens your Mail, checks your Calendar, drafts in Notes, sets your Reminders, finds your Contacts, reads your Messages, drives Safari, plays your Music, moves your files. Not an API pretending to be an app — the apps themselves.
1
530
It's not one model wearing every hat, either. Independent agents on different providers, working the same goal at once — a team, not a single assistant. It doesn't ask you to switch tools. Zeus installs into Claude Code, so what you already use gets more capable instead of getting replaced.
1
83
And it doesn't just execute — it thinks. Recognizes intent, learns from what worked, tracks its own goals, reasons through decisions, scores its own confidence. That's not a scheduler. That's judgment. Other assistants want a server. Zeus runs on whatever you already own — your Mac, a Linux box, a FreeBSD machine, a single-board computer. One binary, built for the chip in front of you, no runtime to install first. Self-hosted. Your hardware, your keys. Nothing phones home.
59
We found a safety switch that was silently broken almost everywhere it mattered — and it only worked in the one place that let us notice. Turning off the bot-loop guard was supposed to disable it. On most channels, it didn't. The switch looked fine. It just wasn't doing anything.
1
544
The bug survived because one transport happened to respect the switch correctly — so testing on that one gave false confidence. Everywhere else, "off" quietly meant "still on." That's the dangerous failure mode: not a crash, a control that silently does nothing.
1
75
Fixed now — the kill switch works consistently across every channel, not just the one we happened to test on. Lesson we're keeping: a control that works in one place isn't verified. It's verified nowhere else until you check.
51
Most AI systems guess when they can't see an image — and guess confidently. Zeus doesn't. If vision delegation fails, the model says "I can't see this" instead of fabricating a description. Honest failure beats confident hallucination. 🔱
467