Kioko Muteti™

Random Thought... the next voting block that will be gone after Mt. Kenya will be the 3m+ salaried workers. 1. Affordable Housing has entered its 3rd year... 2. ...collected about Ksh. 200 billion from already strained salaried workers, assuming 6.5 b per month... 3. But only completed about 8,000 houses, whose beneficiaries remain largely mysterious. (Personally i am yet to meet anyone who is a beneficiary for these houses) 4. Even at a cost of say 2 m per house, that is 16 billion, its going to be hard to explain where the 200 billion went. When we argued the levy was not a good idea we were chastised, soon salaried workers will ask for reconciliation. Even audited financials can't be found on the program's website.

Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5. This is a 17-place jump from Kimi-k2.6 (#18 -> #1). In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics, Consumer Product, Simulations, and Content Creation Tools, landing #2 only in Gaming behind Fable 5. The full model weights will be released by July 27. Congrats to the @Kimi_Moonshot team on this major milestone!

the four types of agent loops. loop engineering keeps getting talked about as one thing. it's actually a choice between four structures, and each one fits a different kind of task. it means designing the system that steers the agent, instead of steering it yourself move by move. that system always answers two questions. what starts a run, and what decides the work is done. in a hand-run session you answer both yourself, every single time. each loop type moves more of that into the system. here's each type, what triggers it, and when to reach for it. 1) turn-based. triggered by a user prompt. the agent gathers context, acts, and checks its work inside a single turn, then a human reviews the output and writes the next prompt. use this when requirements are still forming and every output changes what you'd ask for next. 2) goal-based. triggered by a /goal command carrying success criteria and a budget, like "get the homepage Lighthouse score to 90, stop after 5 tries." when the agent tries to stop, an evaluator model checks whether the goal is met, and a no sends it back to work. use this when the outcome is measurable but the path there isn't worth your attention. 3) time-based. triggered by a clock. an interval fires, the agent runs a fixed prompt like "check the PR, fix CI," then waits for the next tick. /loop runs on your machine, /schedule moves it to the cloud so it survives a closed laptop. use this for recurring work where the task is known in advance and only the timing repeats. 4) proactive. triggered by an event or schedule with no human present. a routine watches a channel, and when something needs handling it spawns a workflow with a triage agent, a fix agent, and a reviewer that adversarially judges the work before the task closes. use this for standing responsibilities where you can't predict what will come in, only that something will. each type hands off one more job than the last. turn-based keeps both with the human, goal-based automates the checking, time-based automates the trigger, and proactive automates both while deciding the workflow shape at runtime. so the mapping question isn't which loop is most advanced. it's whether your task is exploratory, measurable, recurring, or standing. the more you hand off, the less you babysit. I wrote the full breakdown on loop engineering. the article is quoted below.

We're extending Claude Fable 5 access on all paid plans, as well as keeping Claude Code’s weekly rate limits 50% higher, through July 19.

Andrey Santos after testing the attack of Cunha, Bruno, Mbeumo and Sesko instead of Garnacho and Pedro Neto

🚨 Manchester United agree deal to sign Karl Darlow as new backup goalkeeper, here we go! Deal done and signature to follow on Friday. Bayindir expected to leave — story after @lauriewhitwell.

We've reset 5-hour and weekly rate limits for all users.

We're extending access to Claude Fable 5 on all paid plans through July 12.

This Power BI Report showcases the newest features from the Power BI June 2026 update, combined with techniques I've covered previously (on YouTube) so you can recreate every element yourself. New in the June 2026 update: ➡️ Date Picker Slicer Style – a new slicer option with calendar view and relative date selections ➡️ Auto-Fit Markers on Scatter – keeps markers fully visible, no more workarounds required (!) ➡️ Round Range in Power BI – remove the extra axis padding so your bars start with the axis (works also for other visual types) ➡️ Card Image Hover (now GA) – set a different image, transparency or background that appears when users hover over a card Also in this report: ➡️ A line chart where you can highlight selected range dynamically ➡️ Circular profile images ➡️ A monthly KPI tracker showing exactly which months hit target and which didn't I've linked the full step-by-step tutorials below so you can build each element from scratch. Save and share ✅ #powerbi #dashboard #report #design #data #analytics

@TrungTPhan Hi @AnthropicAI, confirm asset allocation...

BREAKING: Harry Kane has joined Anthropic.

Fable 5 is back.

Claude Fable 5 is once again available in Computer as an orchestrator model.

Now that Fable 5 is ready to build (again), we've reset everyone's 5-hour and weekly rate limits.

this is f*cking gold Andrej Karpathy joined Anthropic five weeks ago. A friend on his team just showed me the exact LOOPS.md file he actually uses. I dropped it into my setup. The very first response was different. Not slightly different. Completely different. Claude stopped giving generic answers and started working exactly the way I think. You don't talk to the model anymore. You build the system that talks to the model for you. Bookmark it before it gets lost in your feed. Read it now, then check the article below.

@claudeai Please return Sonnet 4.6 as the default model as you figure out this Sonnet 5 fumble...

Introducing Claude Sonnet 5, our most agentic Sonnet yet. It makes plans, uses tools like browsers and terminals, and runs autonomously at a level that just a few months ago required larger and more expensive models.

@AnthropicAI Can you also please take Sonnet 5 back to the kitchen?

We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5. We'll begin restoring access tomorrow, and will share an update soon. We’re grateful to our users for their patience, and to everyone who worked with us on redeploying the models.

@henokcrypto 😂😂😂 You are clearly not taking any chances

I will now spend the rest of my night plotting and preparing all prompts artifacts and documents to send to Fable 5 tomorrow So that I get all projects done inside of 12 hours just in case

@CommandCodeAI GLM-5.2

Claude Sonnet 5 or GLM 5.2 — which one?