If you are asking engineers to take on product thinking, planning, and risk assessment in addition to their technical work, name it. Define it. Compensate for it. Do not let it happen silently and then wonder why your team is burned out.
AI Made Writing Code Easier. It Made Being an Engineer Harder
www.ivanturkovic.com/2026/02/25/...
The baseline moved, and nobody sent a memo. AI made code cheaper to produce, but made reviewing, understanding, and maintaining it harder. The acceleration trap is real.
The Factory Model: How Coding Agents Changed Software Engineering
addyosmani.com/blog/factor...
You're no longer writing code—you're building the factory that builds the software. Specs become leverage, tests become mandatory, and verification is the bottleneck.
Automate repository tasks with GitHub Agentic Workflows
github.blog/ai-and-ml/a...
GitHub brings coding agents into Actions—write workflow intent in Markdown, run it with guardrails. Triage, docs, testing, and code quality on autopilot. The next layer of CI/CD.
Code has always been the easy part
laughingmeme.org/2026/02/09/...
The cost of code is plunging toward zero. That's genuinely new. But code is the easy part? That's not new at all. The hard part has always been the system—the human-technology hybrid that delivers value and evolves.
Beyond agentic coding
haskellforall.com/2026/02/bey...
Agentic coding promises productivity, but the data says otherwise. A compelling case for "calm" AI tools—semantic browsers, commit splitters, and focus modes—that work alongside you rather than demanding a conversation.
A Guide to Effective Prompt Engineering
blog.bytebytego.com/p/a-guide-t...
Solid primer on the core techniques—zero-shot, few-shot, chain-of-thought, role prompting, and prompt chaining. The key insight: clarity beats complexity.
Agentic Engineering
addyosmani.com/blog/agenti...
Vibe coding ≠ agentic engineering. One is YOLO prototyping, the other is AI implementation with human oversight—with specs, tests, and code review. The terminology matters because the discipline matters.
The Eternal Promise: A History of Attempts to Eliminate Programmers
www.ivanturkovic.com/2026/01/22/...
COBOL, 4GLs, CASE tools, no-code—every decade promises to eliminate programmers. Every decade creates more of them. The hard part was never typing code - it was systems thinking
Good reads from February
If you've been curious about how to write better specs, reduce context drift, or just get more consistent output from your AI tools, Augment is hosting a free virtual event on Friday on spec-driven development.
luma.com/b3u2al1c?tk...
Key insight: Expensive ≠ Quality. Kimi K2.5 is open-source and low-cost, and it was the top performer. The lesson isn't about price — it's about context quality and whether the model actually follows the specification.
Quality: Who did it well?
Kimi went beyond the specification on every dimension and was one of the few to get the edge cases right. Auggie shipped with a broken feature. Big Pickle looked complete on paper; 4 of 11 E2E tests would fail.
Completeness: Who actually finished?
6 of 9 entries finished the task. MiniMax got most of the way there. Gemini produced almost nothing. Big Pickle technically completed it, but 4 of 11 E2E tests crash at runtime. Finished ≠ Working.
😄😄😄
- Kimi K2.5 (OpenCode)
- Warp (Auto)
- Claude Opus 4.6 (Claude Code)
- Claude Sonnet 4.6 (Claude Code)
😐😐😐
- Sonnet 4.6 (Auggie)
- Sonnet 4.6 (OpenCode)
- MiniMax 2.5 (OpenCode)
☹️☹️☹️
- Big Pickle Stealth (OpenCode)
- Gemini 3 Pro
This month's benchmark of AI coding assistants — testing todo app implementations with logic traps across 6 models (Opus, Sonnet, MiniMax, Big Pickle, Gemini 3, and Kimi) and 5 coding agents (Claude Code, Auggie, Gemini, OpenCode, and Warp).
If you're building a terminal-based AI coding agent, it should have:
1. The ability to configure different models for ask vs. act modes.
2. The ability to select an Auto mode, where the model is autoselected depending on the task.
3. Something akin to Claude's insights command.
🚀 Flutter & AI @SoFi: Join us in San Francisco
To dive deep into what’s next, our next Flutter San Francisco Meetup is heading to the SoFi office on Wednesday, February 25th.
RSVP on Luma:https://luma.com/5uzi5ws4
#Flutter #Dart #GenerativeAI #MobileDev #SFTech
Don’t get attached to what you built. Get attached to what you’re trying to achieve.
When you fall in love with specific choices — the architecture, the tool, the approach — you’re forced to get everything right up front. That’s a high bar, and usually the wrong one.
boz.com/articles/ide...
What AI is actually good for, according to developers
github.blog/ai-and-ml/ge...
AGENTS.md outperforms skills in our agent evals
vercel.com/blog/agents-...
How to write a good spec for AI agents
addyosmani.com/blog/good-spec
How does AI impact skill formation?
www.seangoedecke.com/how-does-ai-...
When AI writes almost all code, what happens to software engineering?
newsletter.pragmaticengineer.com/p/when-ai-wr...
How I estimate work as a staff software engineer
www.seangoedecke.com/how-i-estima...
The rise of one-pizza engineering teams
www.jampa.dev/p/the-rise-o...
The third golden age of software engineering
newsletter.pragmaticengineer.com/p/the-third-...
Good tech reads from January...
Standardization = easier adoption, better interop, thriving ecosystem.
It would be nice if spec-driven development tools adopted some standardization.
Every tool has its own:
- Spec format
- CLI interface
- Config structure
Right now we're speedrunning the "14 competing standards" xkcd.
Stranger Things feels like it's just turned into a Wikipedia page for the 80s.
Everyone else: spec-driven-development
Google: context-driven-development
🤣🤣🤣
developers.googleblog.com/conductor-i...
Tools evolve and complexity increases, yet creativity, curiosity, and systems thinking continue to define great developers.
Lowering the barrier for entry doesn't eliminate the need for human expertise—it amplifies it.
www.allthingsdistributed.com/2025/11/tec...
The whole Midoriya wants to save Shigaraki thing seems kinda pointless in retrospect 🤷🏾♂️
These first episodes of Stranger Things aren't hitting for me like it used to.
