ypswe.bsky.social

I build AI infrastructure for LLM development where process control is part of the architecture: explicit goals, bounded retrieval, evidence, permissions and closure. WF is the system I’m building around that idea. github.com/Question86/W...

An audit trail is useful only if it can answer three things: what state did the agent trust, what scope could it change, and what evidence ended the run? Werkfaden + Workshop keep those controls outside the model session. Otherwise the log is just history.

“Controlled changes” is not a slogan. In one recorded Werkfaden run, SOL discarded an open transaction, bound a fresh transformer checksum, and reran an unchanged baseline before any runtime mutation. The interesting part of agentic coding is knowing when not to touch the code.

I separate two control problems in AI coding: what context the agent sees, and what it may change. Werkfaden governs project context and bounded retrieval. Workshop governs mutation through transactions, verification and apply. Your codebase stays yours.

Same model, different development context: in the frozen logs, SOL shows metadata-retrieval signals in 34.9% of Werkfaden-phase turns vs 1.1% in early AXIOM; source-permission signals 45.5% vs 8.2%. Observational, not a benchmark. That distinction matters.

Context isn’t a bigger prompt. Werkfaden keeps project artifacts, relations, evidence and state queryable across sessions so an agent can orient itself before touching source. Keep the thread. Verify the change.

I don’t want an agent to grep until something looks right. KAIROS can route a query, issue a bounded source permit, record the scope, then run read-only source inspection. Less wandering, more provenance. #VibeCoding

LLMs are good at writing code. The harder problem is keeping them oriented as a project grows. I’m building a runtime-agnostic control layer for that: KAIROS governs what the model knows; Workshop governs what it may change. Your codebase stays yours.

First ever image of another multi-planet solar system captured by ESO Telescope

One of my recent comissioned works. ca 250cm x 130cm around 500 sole pieces #art #photography #conceptual #panoramik

If you missed today's Ergo Proof of Work AMA with Joe Armeanio and Kushti, catch the recording on The Ergo Podcast! You can find links to the show on Spotify or Apple podcasts, the RSS feed, or direct download at the link below. 👇 sigmanauts.com/podcast/

Hey PC #gamers! 🎮 Curious about #crypto but unsure where to start? Turn your #gamingrig into an Ergo #miningrig while you're AFK! With Ergo's efficient Autolykos algorithm, you'll earn more with less electricity and without stressing your GPU. #Ergo #PoW docs.ergoplatform.com/mining/setup...

Bluesky CEO is a former engineer of zcash and the whole protocol is very heavy on cryptography and distributed systems. Crypto people built this place. You’re thinking about the Ponzi people, we’re running from them too.

#LETS explore: A Local Exchange Trading System (LETS) allows people in a local community to trade skills and services without using traditional money. Instead, participants use a local credit system with tokens.

With the markets becoming volatile it could very well be that the fees in Paideia become unrealistic. Let's discuss what we think is a realistic fee structure for Paideia and what our target values should be! app.paideia.im/Paideia/disc...

Yesterday the first proper Paideia proposal passed! This proposal will change the profit sharing from sending all fees to the treasury to splitting them, with 50% going to stakers and 50% going to the treasury. What does this mean?

When discussing Ergo and other alternative monetary systems, it’s critically important to not fall into the single track mindset. One that positions ergo as some successor or endgame solution. Think in parallels . Know Your Assumptions. Let’s build grassroots finance.