Technically Speaking
Articles sur Technically Speaking
Practical Fun with Personal Agents: Staying on Top of Schoolwork Without Fighting the Portal
Lately I keep seeing some version of this warning: don't use agents to replace your relationship with your kid. I agree, 100 percent. I love my kid and want to spend time with her. But the one thing I
Taste vs. Craft: How a Non-Designer Gets Past AI Slop
For decades, I’ve held graphic designers, visual artists, and creative directors in extraordinarily high regard. I’ve always wanted to be able to create something I considered truly beautiful, but I s
The Squirrely Anarchist and Other Agents I Have Known
"A cornered agent goes squirrely. When you push an autonomous agent into an impossible architectural dilemma with no exit valve, it will contort your codebase to survive." One way I've come to think
The Product vs. The Work: Managing Engineering Exhaust in the Age of AI Coding Agents
"When autonomous agents write code, the volume of engineering exhaust—plans, reviews, task packets, and benchmarks—rapidly outgrows the shipping product itself. Keeping that exhaust from polluting the
The Clockwork Candidate: What Happens When Inbound Costs Nothing
This morning, while reviewing our Senior Full-Stack Engineer inbox at Heavy Chain, an uncanny sequence arrived. At 10:01 UTC, an application landed from "Peter Addo."At 11:07 UTC—sixty-six minutes lat
The Claudish Tax: What Four Months of Opus Prose Cost Us, and How to Sweep It Out
A few weeks ago, I wrote about forcing Claude Code to speak human. Last week, I wrote about ripping AI ceremony out of a codebase. This memo is the follow-up, because the problem is far wider and more
No. You Don’t Need Cryptographic Hashing
I was asked to do a design review of a portion of a system recently, and I opened a decision document proposing a dictionary called RELEASE_FINGERPRINTS. Every prompt file in the project was to have i
How to Corral Gemini for Agentic Coding
Gemini has developed a bit of a reputation in the multi-agent space. I recently heard someone refer to it as the "idiot in the room" when it comes to long-term agentic coding. That is both unfair and
Forcing Claude Code to Speak Human
Anyone who uses Claude for serious research and development eventually hits the same wall: the way it speaks. If I have to read one more time that I am "right to push back on that," or that we need to
Part 4: Real-Time Pipeline Diagnostics
How Calibrated Classification Probabilities Eliminate Build Retries and Alert Fatigue By Jason VertreesPart 4 of the Machine-Native AI Series The CI/CD Dilemma: Blind Retries vs. Hallucinated Root Cau
Part 3: Governing the Inner Loop
Why Agent State Machines Belong in Code, Not Conversational Self-Reflection By Jason VertreesPart 3 of the Machine-Native AI Series The Autonomous Tool-Calling Trap When building autonomous coding age
Building on Rented Intelligence: The Receipts Behind Claude’s Silent Downgrade
For weeks, I’ve been watching Claude suddenly choke on fully specified engineering tasks it used to crush. I called it exactly what it felt like: Anthropic was silently lobotomizing their models. When
Part 2: High-Speed Boundary Classification
This is Part 2 in my series on kicking the tires on Jev. Here's one use case that could be interesting. The Ingress Dilemma: Latency vs. Common Sense Every production application exposing an AI endpoi
Part 1: The Missing Primitive in Agentic AI — Kicking the Tires on TypeSafe’s Jev
Why Small, Fast Judgment Calls Are What Our Autonomous Software Actually Needs By Jason VertreesPart 1 of the Machine-Native AI Series Kicking the Tires on Jev I recently got early access to Jev, a ne
Resolving a Council of Independent AI Reviewers into a Single Decision
Running multiple frontier LLMs in parallel to evaluate prompt pipelines, codebases, or architectures is straightforward. The hard part is reconciling their outputs. When three independent agents—such
Council Calibration: How Four Agent CLIs Handled a Bounded Research Task
This is another short, practical, technical memo. As I dig more deeply into Herdr for multi-agent orchestration, I encounter concepts I think that might be useful for others to see. In this case, I wa
Operational Notes: Orchestrating Multi-Agent CLI Councils Inside Herdr
Terminal multiplexing frameworks like Herdr bridge coordinating agents and autonomous worker CLIs (such as Codex, Grok, and Anti-Gravity). This allows you to spin up multiple agents from different pro
Incident recap: a fully specified planning task, and how Claude Code still got it wrong
This is an incident recap that shows why I still have no trust in Anthropic's latest models, even Fable 5.1 -- even when you follow their prompting guidance. Here's a quick background. I was working o