"Our thesis is that code should not be maintained - code should be regenerated. Specs should be reviewed, and it’s the specs that you maintain.” by Paul Sawers
https://thenewstack.io/codeplain-spec-driven-regenerative-code/
"Our thesis is that code should not be maintained - code should be regenerated. Specs should be reviewed, and it’s the specs that you maintain.” by Paul Sawers
https://thenewstack.io/codeplain-spec-driven-regenerative-code/

Spec-Driven Development is having a moment. GitHub shipped spec-kit. OpenAI is pushing "natural language as the new programming language." Every AI tooling pitch is a variation of: write the spec, hand it to the model, get the code. The framing is misleading. Dave Farley has been telling you to do this for fifteen years. Dan North coined BDD in 2006. The point was always the same: write requirements in a form that is unambiguous and executable. Code is a byproduct of clearly stating what you want. Most teams ignored it. Gherkin became ceremony. Cucumber became a graveyard. The discipline was right; the payoff was diffuse. What changed isn't the philosophy. It's the economics. BDD asked engineers to do extra work for a payoff they couldn't feel. LLMs punish vague specs in real time — hand a model an ambiguous spec, it confidently ships the wrong thing in twenty seconds. The feedback loop BDD always wanted finally exists, because imprecision now costs you visibly and immediately. The rigor was always the point. AI just made the rigor pay. Practical implication for founders hiring engineers: the people who can actually do SDD well are the people who could have done BDD well. They think in invariants. They write specs that exclude ambiguity. Give them Claude or Codex and they ship like a team of four. Give the prompt-and-pray crowd the same tools and they ship technical debt at four times the rate. Skip "have you used Cursor" in your next interview. Ask them to walk through how they would specify a non-trivial feature before writing any code. The answer tells you everything. | 25 comments on LinkedIn
What are these people seeing that I'm not, what is this level of crazy performance hits that they are talking that I'm not seeing?
https://jeferson.me/blog/2026/06/04/what-are-they-seeing
#AI #Architecture #Artificial #Bubble #Coding #Development #Documentation #Eliza #Game #GameDev #Intelligence #Layoffs #MachineLearning #OpenSource #Productivity #Refactoring #Rsync #Slop #Software #SpecDrivenDevelopment #Turing #VibeCoding #Waterfall
#SoftwareSpecifications can now serve as a dynamic source of truth, as LLM-based reasoning agents become better at interpreting human ambiguity.
The catch? #LLMs are stochastic and must be constrained.
Enter #ContextEngineering - a structured discipline focused on providing clear intent and missing instructions to AI models.
It relies heavily on context artifacts, including: ⇨ Skills ⇨ Rules ⇨ Scripts ⇨ Feedback loops ⇨ Evaluation metrics
🎧 Hear more insights on the #InfoQ #podcast with Baruch Sadogursky: https://bit.ly/49dArFj
📄 #transcript included
#SoftwareArchitecture #SpecDrivenDevelopment #Testing #AI #SoftwareEngineering
On 3 June I'll be presenting at #PyData Johannesburg, South Africa.
I'll be sharing some details of my own #SpecDrivenDevelopment #Agentic #SoftwareEngineering workflow.
RSVP here: https://www.meetup.com/pydata-johannesburg/events/314582868
Also, I have a few #ClaudeMax vouchers to give away while I'm there (Thanks #Anthropic )
Cory House presents 'Automating Quality with AI' this July at Nebraska.Code().
https://nebraskacode.amegala.com/
#AIGuardrails #GeneratedTests #SpecDrivenDevelopment #Nebraska #AIPrompting #ContextManagement #LLM #TechnologyConference #CoryHouse #DevConference #Programming #QualityAI #AISlop
« J'ai découvert gh-issue-sync »
https://notes.sklein.xyz/2026-05-09_1008/zen/
#JaiDecouvert #TIL #GitHub #issue #SpecDrivenDevelopment #AIagent #OpenCode