Unisone Profile Banner
zay Profile
zay

@Unisone

Followers
1K
Following
12K
Media
563
Statuses
6K

AI‑native full‑stack builder | agent infra, MCP servers, prompts, AI tools and Claude Code skills

Washington, DC
Joined September 2014
Don't wanna be here? Send us removal request.
@Unisone
zay
10 days
New release: openclaw-config v2026.03.06 What's in it: STEPPS scoring framework (50-point content quality system) Automated reel pipeline (JSON → Instagram Reel) Multi-agent architecture v2 Taskrunner with delivery auditing Production configs for running OpenClaw as a real
Tweet card summary image
github.com
Production-tested configs, scripts, and workspace templates for OpenClaw. Hardening guides, memory engine, skill routing, agent personas, and CI security scanning. - unisone/openclaw-config
0
0
1
@tricalt
Vasilije
5 days
77
348
3K
@bcherny
Boris Cherny
3 days
We doubled Claude usage on weekends, and outside 5–11am PT on weekdays for the next 2 weeks.
@claudeai
Claude
3 days
A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.
352
318
7K
@claudeai
Claude
4 days
1 million context window: Now generally available for Claude Opus 4.6 and Claude Sonnet 4.6.
1K
2K
25K
@trq212
Thariq
5 days
the generative UI dream is happening
@claudeai
Claude
5 days
Claude can now build interactive charts and diagrams, directly in the chat. Available today in beta on all plans, including free. Try it out: https://t.co/tHPAZRgQkn
118
109
4K
@WatcherGuru
Watcher.Guru
8 days
JUST IN: Brent crude oil surges to $115, up 25% today.
406
1K
7K
@Unisone
zay
8 days
The good: Massive scope — covers a full virtual agency roster from frontend dev to legal compliance to XR design. Solid for someone thinking “what roles could I prompt an AI into?” Consistent structure — every agent has identity, mission, critical rules, deliverables with
@karpathy
Andrej Karpathy
10 days
I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the
0
0
1
@karpathy
Andrej Karpathy
10 days
I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the
1K
4K
28K
@Unisone
zay
16 days
This is basically a free computational finance course wrapped in a Twitter article
0
1
1
@addyosmani
Addy Osmani
12 days
Introducing the Google Workspace CLI: https://t.co/8yWtbxiVPp - built for humans and agents. Google Drive, Gmail, Calendar, and every Workspace API. 40+ agent skills included.
Tweet card summary image
github.com
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills. - googlework...
654
2K
15K
@vercel_dev
Vercel Developers
15 days
Proud to support @openclaw on Vercel.
@openclaw
OpenClaw🦞
15 days
Open source at scale needs friends. @vercel stepped up and sponsors https://t.co/dOPvdvNrLp + https://t.co/GnEYfnSCLB. Grateful. 🦞
52
109
2K
@Unisone
zay
16 days
This is basically a free computational finance course wrapped in a Twitter article
0
1
1
@gemchange_ltd
gemchanger
17 days
137
715
7K
@AutismCapital
Autism Capital 🧩
17 days
Summary of the AI wars:
@sama
Sam Altman
17 days
Tonight, we reached an agreement with the Department of War to deploy our models in their classified network. In all of our interactions, the DoW displayed a deep respect for safety and a desire to partner to achieve the best possible outcome. AI safety and wide distribution of
139
696
10K
@Unisone
zay
17 days
there we go
@sama
Sam Altman
17 days
Tonight, we reached an agreement with the Department of War to deploy our models in their classified network. In all of our interactions, the DoW displayed a deep respect for safety and a desire to partner to achieve the best possible outcome. AI safety and wide distribution of
0
0
1
@Unisone
zay
17 days
I don't work at Anthropic - but now I want to! The Pentagon demanded they drop safeguards on autonomous weapons and mass surveillance. Dario said "we cannot in good conscience accede." Trump responded by banning them from federal contracts. When every other Al company
@AnthropicAI
Anthropic
19 days
A statement from Anthropic CEO, Dario Amodei, on our discussions with the Department of War. https://t.co/rM77LJejuk
0
2
2
@ilyasut
Ilya Sutskever
18 days
It’s extremely good that Anthropic has not backed down, and it’s siginficant that OpenAI has taken a similar stance. In the future, there will be much more challenging situations of this nature, and it will be critical for the relevant leaders to rise up to the occasion, for
1K
2K
26K
@Unisone
zay
18 days
Just shipped openclaw-config v2026.02.27 🦞 What's new: → Session Management Suite — autonomous watchdog that detects bloated/stuck sessions and cleans them up. No more manual purging. → Model Change Safety Rules — the thinking-block signature problem documented. If you've ever
Tweet card summary image
github.com
Production-tested configs, scripts, and workspace templates for OpenClaw. Hardening guides, memory engine, skill routing, agent personas, and CI security scanning. - unisone/openclaw-config
0
1
3
@MilkRoadAI
Milk Road AI
19 days
Layoff Announcements: 1. US Government (DOGE): 317,000 employees 2. UPS: 78,000 employees 3. Amazon: 30,000 employees 4. Intel: 25,000 employees 5. Citigroup: 20,000 employees 6. Nissan: 20,000 employees 7. Nestlé: 16,000 employees 8. Microsoft: 15,000 employees 9. Bosch:
@jack
jack
19 days
we're making @blocks smaller today. here's my note to the company. #### today we're making one of the hardest decisions in the history of our company: we're reducing our organization by nearly half, from over 10,000 people to just under 6,000. that means over 4,000 of you are
651
2K
7K