Nostr notes by asyncmind:
Software Isn’t the Battle. It’s the Battlefield Generator. ...
Software Isn’t the Battle. It’s the Battlefield Generator. ...
asyncmind (npub1zm…wyppc)
asyncmind on Nostr:
Software Isn’t the Battle. It’s the Battlefield Generator. Most developers don’t use BDD. Not because they can’t— but because the system doesn’t reward it. And that’s the part no one wants to admit. https://npub1zmg3gvpas
Nostr notes by asyncmind:
> BDD stands like Krishna in the battlefield. ...
> BDD stands like Krishna in the battlefield. ...
asyncmind (npub1zm…wyppc)
asyncmind on Nostr:
> BDD stands like Krishna in the battlefield. https://npub1zmg3gvpasgp3zkgceg62yg8fyhqz9sy3dqt45kkwt60nkctyp9rs9wyppc.blossom.band/d4b65d17da65f53012b9f0a707788dd0fd49b2c7cb88a18ddc181522b5c0cb7f.jpg Not to fight— but to bring clarity. I
Nostr notes by asyncmind:
The Disappearance of Narrative Power Power is shifting— from ...
The Disappearance of Narrative Power Power is shifting— from ...
asyncmind (npub1zm…wyppc)
asyncmind on Nostr:
The Disappearance of Narrative Power Power is shifting— from those who control narrative → to those who can anchor verifiable events in time. https://npub1zmg3gvpasgp3zkgceg62yg8fyhqz9sy3dqt45kkwt60nkctyp9rs9wyppc.blossom.band/b34c6832
OpenClaw🦞 / #openclaw:
OpenClaw 2026.4.11 is out
✨ big polish drop for stability
🛡️ safer provider transport/routing
🤖 more reliable subagents + exec approvals
💬 lots of Slack / WhatsApp / Telegram / Matrix fixes
🌐 browser + mobile cleanup
a chunky cleanup pass 😎https://github.com/openclaw/openclaw/releases/tag/v2026.4.11
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.4.11 is out
✨ big polish drop for stability
🛡️ safer provider transport/routing
🤖 more reliable subagents + exec approvals
💬 lots of Slack / WhatsApp / Telegram / Matrix fixes
🌐 browser + mobile cleanup
a chunky cleanup pass 😎https://github.com/openclaw/openclaw/releases/tag/v2026.4.11
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
GitHub
Release openclaw 2026.4.11 · openclaw/openclaw
Changes
Dreaming/memory-wiki: add ChatGPT import ingestion plus new Imported Insights and Memory Palace diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full s...
Dreaming/memory-wiki: add ChatGPT import ingestion plus new Imported Insights and Memory Palace diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full s...
OpenClaw🦞 / @openclaw:
RT by @openclaw: Two experiments in the next @openclaw to address some "GPT is lazy" issues:
1) Strict mode:
agents.defaults.embeddedPi.executionContract = "strict-agentic"
This tells GPT-5.x to keep working: read more code, call tools, make changes, or return a real blocker instead of stopping at “here’s the plan.” https://docs.openclaw.ai/providers/openai
RT by @openclaw: Two experiments in the next @openclaw to address some "GPT is lazy" issues:
1) Strict mode:
agents.defaults.embeddedPi.executionContract = "strict-agentic"
This tells GPT-5.x to keep working: read more code, call tools, make changes, or return a real blocker instead of stopping at “here’s the plan.” https://docs.openclaw.ai/providers/openai
Peter Steinberger 🦞 / @steipete:
RT by @steipete: OpenAI is working on a new experimental feature for Codex called Scratchpad.
Users will be able to start multiple Codex chats from a TODO list view, which will be executed in parallel.
It will become very instrumental in the upcoming Codex Superapp, where you will be able to trigger a broader range of tasks to achieve your goals.
* Not available yet 👀
RT by @steipete: OpenAI is working on a new experimental feature for Codex called Scratchpad.
Users will be able to start multiple Codex chats from a TODO list view, which will be executed in parallel.
It will become very instrumental in the upcoming Codex Superapp, where you will be able to trigger a broader range of tasks to achieve your goals.
* Not available yet 👀
Peter Steinberger 🦞 / @steipete:
Two experiments in the next @openclaw to address some "GPT is lazy" issues:
1) Strict mode:
agents.defaults.embeddedPi.executionContract = "strict-agentic"
This tells GPT-5.x to keep working: read more code, call tools, make changes, or return a real blocker instead of stopping at “here’s the plan.” https://docs.openclaw.ai/providers/openai
Two experiments in the next @openclaw to address some "GPT is lazy" issues:
1) Strict mode:
agents.defaults.embeddedPi.executionContract = "strict-agentic"
This tells GPT-5.x to keep working: read more code, call tools, make changes, or return a real blocker instead of stopping at “here’s the plan.” https://docs.openclaw.ai/providers/openai
Peter Steinberger 🦞 / @steipete:
R to @steipete: 2) Native Codex as the OpenClaw harness:
plugins.entries.codex.enabled = true
agents.defaults.model = "codex/gpt-5.4"
agents.defaults.embeddedHarness = { runtime: "codex", fallback: "none" }
Codex owns threads, resume, compaction, app-server execution. https://docs.openclaw.ai/plugins/codex-harness
R to @steipete: 2) Native Codex as the OpenClaw harness:
plugins.entries.codex.enabled = true
agents.defaults.model = "codex/gpt-5.4"
agents.defaults.embeddedHarness = { runtime: "codex", fallback: "none" }
Codex owns threads, resume, compaction, app-server execution. https://docs.openclaw.ai/plugins/codex-harness
Peter Steinberger 🦞 / @steipete:
R to @steipete: Harnesses can now been plugins - meaning it'd be trivial to replace the default Pi harness with e.g. Anthropic’s SDK or another custom one.
This won't magically allow Claude subscription, but it's useful to compare different implementations.
Using codex as harness will likely weaken personality, but should increase agentic mode to keep the agent working on longer-horizon tasks.
So far I gated strict mode to GPT since it's not yet tested with other models, but it's trivial t...
R to @steipete: Harnesses can now been plugins - meaning it'd be trivial to replace the default Pi harness with e.g. Anthropic’s SDK or another custom one.
This won't magically allow Claude subscription, but it's useful to compare different implementations.
Using codex as harness will likely weaken personality, but should increase agentic mode to keep the agent working on longer-horizon tasks.
So far I gated strict mode to GPT since it's not yet tested with other models, but it's trivial t...
Peter Steinberger 🦞 / @steipete:
RT by @steipete: MiniMax M2.7 is available on Ollama's cloud, and is licensed for commercial usage.
Use it with OpenClaw:
ollama launch openclaw --model minimax-m2.7:cloud
Coding agents, such as Claude:
ollama launch claude --model minimax-m2.7:cloud
Chat with the model:
ollama run minimax-m2.7:cloud
RT by @steipete: MiniMax M2.7 is available on Ollama's cloud, and is licensed for commercial usage.
Use it with OpenClaw:
ollama launch openclaw --model minimax-m2.7:cloud
Coding agents, such as Claude:
ollama launch claude --model minimax-m2.7:cloud
Chat with the model:
ollama run minimax-m2.7:cloud