Leading design agency transforming Madagascar’s agri-tech sector with human-centered design, open-source tech, AI and no-code MVPs.Built by @Fenohery_fata.plus AntananarivoJoined April 2024
Introducing the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format.
AI is only as smart as the context we give it. As we build more advanced, agentic AI systems, they need accurate metadata and context to be useful. But in most organizations, that context is locked inside fragmented data catalogs, isolated wikis, scattered code comments, or the minds of senior engineers. Every time a new AI agent is built, teams are forced to solve the exact same context-assembly problem from scratch.
To solve this, we've announced OKF, a vendor-neutral, open specification that formalizes the "LLM-wiki pattern" into a portable, interoperable format. It provides a standardized way to represent the enterprise knowledge that modern AI systems rely on.
— Just markdown: readable in any editor, renderable on GitHub, indexable by any search tool
— Just files: shippable as a tarball, hostable in any git repo, mountable on any filesystem
— Just YAML frontmatter: for the small set of structured fields that need to be queryable: type, title, description, resource, tags, and timestamp
We’ve also shipped reference implementations to help you hit the ground running, including an enrichment agent for BigQuery, a static HTML visualizer, and live sample bundles on @github → goo.gle/4uGvAEe
➕ Knowledge Catalog can now natively ingest OKF!
Stop reinventing data models and building bespoke integrations for every new AI tool. Here's more about how OKF works → goo.gle/4uGvBbg
Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere.
GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans.
docs.z.ai/devpack/latest…
As our new flagship model, GLM-5.2 delivers
Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere.
GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans.
docs.z.ai/devpack/latest…
As our new flagship model, GLM-5.2 delivers
GLM-5.2 is Fully Open, Frontier Intelligence Belongs to Everyone
Today, the sudden restriction of certain frontier models is deeply regrettable. At a time when access to frontier models is abruptly cut off for non-technical reasons, we are even more convinced of one thing: science should be global.
The path to AGI (Artificial General Intelligence) must never be enclosed by high walls. We have always believed that AGI should be the cornerstone for all of humanity to collaboratively explore the boundaries of intelligence and solve complex challenges, rather than a privilege monopolized by a few rules and subject to revocation at any moment. In the face of external blockades and restrictions, our attitude is one of radical openness. Frontier intelligence must remain open-source, accessible, and buildable, serving every dedicated developer.
GLM-5.2 is Zhipu's most capable open-source model to date. It not only supports a truly usable 1M context window but also maintains a continuous lead in the independent completion of long-horizon tasks, providing solid foundational support for building complex agent applications. It also continues to be our main engine for creating the strongest domestic coding model.
Tonight at 5:21—at this special moment—GLM-5.2 will officially be available to all GLM Coding Plan users (including Lite / Pro / Max). The API will also go live next week.
A step closer to frontier intelligence for everyone.
The future of AI is open, and it is for the people.
ModelKey: GLM-5.2
GLM-5.2 is now fully available for GLM Coding Plan users.
ZCode 3.0 is deeply optimized for GLM-5.2, bringing stronger Agent task execution, better long-context coding, and the new Goal feature for managing larger development objectives from planning to completion.
Coding Plan subscribers get 150% usage quota inside ZCode. New users get 5 days free with 5M tokens per day.
Download: zcode.z.ai
Skills in Gemini Enterprise let you formalize a specific workflow—like applying brand guidelines or formatting a report—and save it as a reusable action for your whole team.
Learn more about codifying your unique expertise into reusable Skills → goo.gle/4d5sUKL
Claude Code fully dissected!
Researchers from UCL reverse-engineered the leaked Claude source. What they found changes how you should think about agent design.
Only 1.6% of the codebase is AI decision logic.
The other 98.4% is operational infrastructure. Permission gates, tool routing, context compaction, recovery logic, session persistence. The model reasons. The harness does everything else.
This is the opposite of what most agent frameworks do today.
LangGraph routes model outputs through explicit state machines. Devin bolts heavy planners onto operational scaffolding. Claude Code gives the model maximum decision latitude inside a rich deterministic harness, and invests all its engineering effort in that harness.
The core loop is a simple while-true. Call model, run tools, repeat.
But the systems around that loop are where the real design lives:
A permission system with 7 modes and an ML classifier. Users approve 93% of prompts anyway, so the architecture compensates with automated layers instead of adding more warnings.
A 5-layer context compaction pipeline. Each layer runs only when cheaper ones fail. Budget reduction, snip, microcompact, context collapse, auto-compact.
Four extension mechanisms ordered by context cost. Hooks (zero), skills (low), plugins (medium), MCP (high). Each answers a different integration problem.
Subagents return only summary text to the parent. Their full transcripts live in sidechain files. Agent teams still cost roughly 7x the tokens of a standard session.
Resume does not restore session-scoped permissions. Trust is re-established every session. That friction is the point.
The bet behind all of this is simple. As frontier models converge on raw coding ability, the quality of the harness becomes the differentiator, not the model.
Paper: Dive into Claude Code (arXiv:2604.14228)
We've shared an article on Agent Harness and what every big company is building.
Read it below.
This is really big news. Google introduced the Open Knowledge Format (OKF) - a standardized way to store information in a directory of markdown files. Makes it really easy to make a digital brain that agents can use.
These files can serve as a living wiki. You can give agents the ability to query them or edit them. They can interlink.
Seems to me this could replace Notion or Obsidian. I can think of so many uses for this.
Google's blog post: cloud.google.com/blog/products/…
An easier to understand explanation is the SPEC.md file:
github.com/GoogleCloudPla…
I gave those two links to Antigravity and asked how we could use it for any of the projects we're working on. It came up with so many ideas. I would imagine Claude Fable 5 would whip up some pretty amazing things based on this system.
Currently creating an OKF library of our pepper garden. It's going to be a fun weekend.
Building a mobile app means wrestling with Xcode, Android Studio, certificates, builds, and more
@expo removes most of that pain
• Build iOS + Android apps with React Native
• 100+ ready-made native APIs
• Cloud builds and app store submissions
• Push updates without waiting for app reviews
• One workflow from development to deployment
Karpathy said something you'll regret ignoring:
"Remove yourself as the bottleneck. Maximize your leverage. Put in very few tokens, and a huge amount of stuff happens on your behalf."
Loop engineering is the exact thing that does that.
In a hand-run session, the operator handles two things:
- deciding what the agent runs next
- and checking its output before the next step
Both are manual, and both decide how far the agent gets on its own without the operator.
Loop engineering moves both steps into the system.
A core operating structure surrounds the loop, and the diagram below depicts it.
- A schedule decides what to run
- Loop is the maker that produces the work
- A separate checker agent grades the output
- A file on disk holds the state they both read.
The loop runs until either done, max iterations, or an exhausted budget.
Here are some practical engineering considerations:
1) A model grading its own output justifies what it already did instead of catching where it failed.
That's why a separate checker's findings return to the maker as the next instruction. And the cycle repeats until the checker finds nothing left to fix.
2) A loop with no stop condition burns tokens, and the cost climbs fast once sub-agents and long runs add up.
That's why the exit must be set before the loop runs, not while it is running.
A simple exit could be:
↳ fix only the major issues, run one final pass, and stop after two loops, with "all tests pass and lint clean" as the rule that ends it.
3) State has to live on disk, not in context.
The model forgets everything between runs, so an MD file or a knowledge graph holds what is done and what is still open.
Each run reads it and writes back to it, which lets a loop pick up again after days.
4) The lower the verification bar, the safer the loop.
Boring, repetitive checks like a stale version string or a missing test are trivial to verify, so a loop runs them with little risk while the operator is away.
Judgment-heavy work is loopable too, but only as far as the checker can confirm the result.
Let's look at how an unattended loop fails in two ways.
1) It reports done when nothing is actually verified.
The separate checker exists to prevent it, but it merges code faster than anyone reads it, so over weeks, the team stops understanding its own codebase while every check stays green.
Green tests say the code passed the tests, not that anyone knows what shipped. Someone still has to read what the loop merges.
2) The checker keeps a running loop honest, but it only catches failures inside a run.
The harness around the loop, like the prompts, tools, and checks wrapped around the model, still drifts and breaks in production as models change.
That repair loop is usually run by hand based on observability traces.
My co-founder wrote a detailed walkthrough (with code) on making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it cannot recur.
Read it below.
275 Followers 2K FollowingLead UX Designer & CEO at Jumatechs | UI/UX Design/ Development for SaaS, Fintech, MVP & Mobile Apps | Trusted by 80+
✦ Dribbble: https://t.co/T49sUEGQbe
4K Followers 2K FollowingVP Software Engineer @ Goldman Sachs. I write about Tech and AI. Building ✨https://t.co/N3QkOqUTr5 ✨- Global AI news feed, all stories ranked in real time.
3K Followers 458 FollowingJe construis des apps sur mesure pour les PME qui en ont marre d'Excel | +15 projets | CEO @ https://t.co/VYEeo6CMXS
Working on : https://t.co/ENtyLsrloq
2K Followers 544 FollowingAgronomist | Expert in sustainable farming practices 🌱 | Dedicated to improving crop yields and soil health | Follow for insights and tips!
1K Followers 889 FollowingAstronaut, Accountant, Doctor, Lawyer, Investment Banker and CEO - I'm none of these things. I like building stuff online though.
148 Followers 1K Followingكلمة التوحيد هي( لا إله إلا الله) تعني الإيمان بأن الله واحد في ذاته وصفاته وأفعاله، ولا شريك له في ملكه وتدبيره، وأنه وحده المستحق للعبادة. وهي أعظم الذكر عن
7K Followers 2K Following|| Animal Production Department || University of Rwanda_ UR|| Passionate about Farm Consultancy & Proud Animal scientist by Career & Professional 🐓🐄🐖🐇🦮🩺!
426 Followers 7K FollowingI won the America Lottery on Powerball and I'm willing to give out $500,000K to
my first 1k followers, we rise by lifting others, just Dm
"WEST I FOLLOWED"
726 Followers 4K FollowingThrough assembling & distributors of agro-processing equipment,driven to improve agriculture production by automation and mechanization. call us +250795600124
1K Followers 2K FollowingYo Space is a youth edutainment platform for young people to express their views on corruption and the future of Uganda /Sundays 5PM EAT on @ubctvuganda
14 Followers 435 FollowingWe are into Farming and Agro commodities supplies.
We farm fresh Sweet Bell Pepper (Red & Yellow) & Ginger
wa me +2349096578978.
547 Followers 2K FollowingIndependent media for strategic analysis on Africa. Articles, investigations, politics and economy. Understanding African dynamics and global challenges.
14K Followers 11K FollowingAI Artist Exploring Rural Worlds / Inspired by Farms, Fields & Folklore /Supporting Local Farmers Markets #RuralArt
I am also a small farmer
4K Followers 16 FollowingNex: A next-gen platform linking models, data, and frameworks. We provide a stable, high-performance, ready-to-use agent system.
8K Followers 6 FollowingHyperagent is the system of agents that does real work, learns how your organization operates, and deploys across your entire team. By the team at Airtable.
232K Followers 2K Following#Defi analyst || Crypto Researcher || Sharing my research work in defi and web3 generally || Now exploring the possibilities of Ai
277K Followers 438 FollowingRivelino (@alpharivelino) is the creator of the green line test. His work has been featured in the New York Post, Newsweek, HuffPost, Daily Mail and Fox News
3K Followers 3K FollowingI care about humans, computers, and interfaces. But mostly humans.
Currently @apple, previously @magicleap @mit
I'm also at https://t.co/ARipvq68fw
5K Followers 13 FollowingContinual learning for stateful agents. SOTA & pareto dominant—accuracy, speed, cost, efficiency. Memory that reasons. Built by @plasticlabs.
120K Followers 3K FollowingDream realized! Turned my love for AI into a career - sharing daily. Get my newsletter (225k+ subs): 🔗 https://t.co/jHMmImnfVg //📧 [email protected]
1K Followers 2K FollowingI am the one and only Crypto Hulk! I am here to help you survive this Crytpo space. Don't be a sheep! Follow the Crypto Hulk! REAL TALK! Not Financial Advice!