I have seatbelt configured for both and even wrote a guide on how to set it up. This assumes MacOS though pragmaticvectors.com/posts/m… Same discipline applies at work as well with cli agents sandboxed and scoped to the exclusive repos they’re supposed to touch. So multiple .sb files

Quitting programming as a career right now because of LLMs would be like quitting carpentry as a career thanks to the invention of the table saw.

OpenAI’s first device is a smart speaker without a display and costs $300+. Here is a ChatGPT mock-up based on article: ▫️doughnut/ring shape ▫️size of a hockey puck ▫️have camera, speakers, microphone, lights ▫️interactive moving parts to make it feel “more alive” than existing smart speaker ▫️will use high-quality metal (a Jony Ive staple) ▫️Apple’s lawsuit alleges OpenAI took trade secrets for metal finishings but Apple doesn’t have a portable smart speaker ▫️carry-able around the house with one hand ▫️ “The battery-powered item will be designed to work in different positions — in a user’s hand, say, or placed on a nightstand or kitchen counter.”

HomeClaw lets you use any agent to control your Apple Home. It has a CLI, MCP and @openclaw Plugin. You can literally do anything from the command line and agent including creating and importing scenes. Also this is my first MacOS app published to the App Store. homeclaw.omarknows.app

🧵 Researchers ran the same 22 enterprise tasks on six different foundation models— Claude Sonnet 4.6, Gemini 3.1, Flash 3.5, Qwen 3.6, GLM 5.1, P almyra X6. Same prompts. Same judges. Same price table. Only one thing changed: the orchestration layer around them. What happened? 1/ The bill for every single model dropped 33% to 61%. Median latency fell 44%. Tokens per task dropped 38%. And headline quality? Held at parity. On this workload, the orchestration layer moved cost more than switching between the cheapest and most expensive model did. 2/ The dominant pattern in agentic AI today is what we call token maxing: Buying capability by throwing more tokens at it—longer reasoning traces, wider tool catalogs, full history replays every turn. Falling per-token prices mask the pattern. But total spend rises anyway. 3/ The decisive lever isn't the model. It's the harness—the orchestration layer that: • Assembles context • Exposes tools • Sequences turns • Delegates work • Governs failures The harness controls every input token except the model's own verbosity. Which means it controls the bill. 4/ Here's the cost formula for one agentic task (Eq. 1): C = Σ (p_in × T_in + p_out × T_out) The input side breaks down into terms the harness builds: T_in = System + History + Tool schemas + Retrieval + User turn Four of five terms? Pure code decisions. 5/ A naive loop replays the full transcript every turn. Total input tokens grow quadratically: O(k²) in turn count. A harness that caches the stable prefix, compacts history, and offloads bulky tool outputs converts that to O(k). Same model. Radically different bill. 6/ Two further facts sharpen this. Agent workloads are input-dominated. Measured ratios are ~100:1. So the p_in term is nearly the whole bill. Prompt caching prices cache reads at ~0.1× list. If you can hold 99.9% of your prompt stable, you pay a tenth of list for the dominant cost term. 7/ The researcher's harness does exactly that with cache-shape discipline: A byte-stable prefix (tool schemas + stable system prompt + append-only transcript) + a volatile tail rebuilt each turn (clock, plan, reminders). Measured: 99.9% of tokens served as cache reads. The same mechanism that cuts the bill also cleans the model's working set. 8/ Six mechanism families implement the harness: 1. Cache-shape discipline (two-zone prompt) 2. Structured, incremental, cache-aware compaction 3. Context offload (sub-agent firewalls, filesystem pointers) 4. Zero-token waiting (durable suspends, not polling) 5. Failure-spend governance (typed failures, circuit breakers) 6. Model-agnostic floor (normalized streams, native tool calling) 9/ Quality moved with capability. Researchers measured quality gain vs. baseline strength across six models. Correlation: r = 0.99 Stronger models extract more quality from the same harness. Weaker models can be overwhelmed by it. We call this harness leverage. 10/ The harness also added one net-new capability: sub-agent delegation (spawn a scoped child, cap its summary at 8 KB, merge results). But it only crossed a usable reliability threshold on the two strongest models (0.85–0.86). Orchestration features carry capability floors. 11/ Per-model cost reductions: • Sonnet 4.6: −39% • Gemini 3.1: −33% • Flash 3.5: −61% • Qwen 3.6: −44% • GLM 5.1: −47% • Palmyra X6: −52% Every. Single. One. That's the signature of a layer-level effect, not a model-specific trick. 12/ Now, fleet economics. At one million agent tasks per month: Baseline: $210k/month Harness: $120k/month Savings: $90k/month. $1.08M/year. From orchestration alone. And it stacks across every model, every vendor migration, every unit of volume. 13/ Three properties make harness savings compound: • Model-portable: implemented above the API, applies to models that don't exist yet. • Volume-linear: grows with exactly the quantity (agentic task volume) growing fastest. • Stackable: multiplies with routing, per-token price declines, and prompt-level compression. 14/ The managerial fix is a measurement fix. Teams that report quality alone will token-max, because tokens are someone else's line item. The escape: CPM (task-completions per million tokens) and η$ (quality per dollar). We moved CPM from 54.9 to 92.0—opposite to the industry trajectory—while quality held. 15/ One caveat: the harness regressed quality on one task (multi-step research synthesis, 0.80 → 0.60). The regression was driven by the smaller models. The honest reading of n=22: lead with efficiency (uniform, decisive), not quality (directional). 16/ The broader claim: token maxing is a choice made at the orchestration layer, and it can be unmade there. Mechanism by mechanism: • Cache the stable • Compact the old • Offload the bulky • Suspend the waiting • Bound the failing 17/ The contrarian takeaway: "Model choice is now a rounding error compared with orchestration hygiene." "The fastest way to raise quality per dollar is to stop showing the model 60% of the tokens it currently sees." "Sub-agent delegation is not a feature—it is a capability tax that only frontier models can afford to pay." 19/ The strategic conclusion: An organization that rents its orchestration layer has outsourced the variable it controls most. The harness is not plumbing. On the evidence here, it's the P&L. Paper: arxiv.org/abs/2607.06906

Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.