Interview with Andrej Karpathy (OpenAI co-founder, former Tesla Autopilot) moving from *vibe coding* to *agentic engineering*: December 2025 as the turning point "never felt more behind as a programmer," the Software 1.0/2.0/3.0 taxonomy, the openclaw example (bash script → text to copy-paste into the agent) and MenuGen rendered obsolete by Gemini's Nanobanana, the *verifiability* theory explaining why LLMs are *jagged* (math/code peak, "walk to the car wash 50m away" fails), the distinction between *vibe coding* (raise the floor) and *agentic engineering* (preserve the quality bar), the "animals vs ghosts" metaphor, the overhaul of hiring via agent-versus-agent projects, and the key formula: ***"You can outsource your thinking but you can't outsource your understanding."***
#Andrej Karpathy#vibe coding#agentic engineering
Andrej Karpathy (co-fondateur OpenAI, ex-Tesla Autopilot, créateur du terme "vibe coding")
Manifesto-style X thread by Rohit (@rohit4verse) laying out the *2026 AI engineer roadmap*: a $150k gap between prompt engineer and systems architect, the end of *generic wrappers* "sherlocked by big tech," and 5 portfolio projects ranked by complexity level (offline mobile SLM, self-improving coding agent, multimodal *Cursor for video editors*, privacy-first personal life OS agent, autonomous enterprise workflow agent). Each project describes its *key architectural decisions* (lazy loading, sliding window, sandboxing, scene detection, personal knowledge graph, event-driven multi-agent, audit trail, RBAC, observability). Structuring slogan: *"the replaceable: building wrappers / the unfireable: shipping autonomous systems"*. Injunctive, viral tone typical of X in 2026.
#2026 AI engineer roadmap#Rohit#rohit4verse
Rohit (@rohit4verse) — créateur de contenu IA sur X · vulgarisateur d'architecture et roadmaps de carrière en ingénierie IA.
Post from the **Ahrefs blog** published on **April 28, 2026** by **Ryan Law** (Director of Content Marketing, Ahrefs) describing an in-house **content engineering** system built around **Claude Code**: an editorial pipeline that produces **publish-ready drafts in 6 to 12 minutes**. **Pivot thesis**: ***« AI content is not, by default, good. This process works well because it mirrors our existing human editorial process »*** — quality doesn't come from the model but from the **faithful reproduction of a human editorial process** proven over decades. Architecture: **~23 skill files**, each corresponding to an editorial step (keyword research, topic gap analysis, structural outlining, research compilation, draft generation, formatting), **orchestrated by a master skill `blog-pipeline`** that chains them to produce a complete article. **Seven design principles**: (1) **mimic human workflows** by chaining skills adapted from existing Ahrefs editorial documentation; (2) **output each step separately** for troubleshooting (*« if you get an article at the end of a ten minute run, and it's bad, it's hard to diagnose precisely where and why the process went wrong »* → save intermediate outputs); (3) **create test cases** via Anthropic's `skill-creator` skill to evaluate and improve guidance; (4) **plug in quality data sources** — the **Ahrefs MCP** (keyword metrics, parent topic, long-tail themes, SERP overviews, competitive analysis), competitive analysis and product docs; (5) **front-load human direction** via context parameters enabling editorial guidance; (6) **build interactive previews** in HTML format for review before publication; (7) **allow customization** (each team member can fork and modify the system). **Volume**: ~**15 articles published** and ~**30 articles updated** via this workflow; development started in **February 2026** (the prior process from **August 2025** took several days and manual intervention). **Explicit caveats** (anti-oversell): *« experience matters »* — the process reflects decades of editorial expertise; topic selection focuses on **informational SEO content** the author knows well; Ahrefs **has no plan to "scale" content massively** but maintains an **evergreen library**. Philosophy: automate *« the formulaic parts of work »* to eliminate drudgery and free up time for research, thought leadership, webinars, and system optimization — **not** replace human effort. Canonical reference cited by Pasquale Pillitteri (*Opus 4.8 SEO workflow*) as field proof of the « 6-12 min/draft » gain. Direct convergence with the **skills-over-prompts** doctrine (Lattice, PROJ-AI), **systems around the model** (Dropbox/Okumura), and the use of **HTML as a review artifact** (Shihipar).
**Ryan Law** — Director of Content Marketing chez **Ahrefs**. Praticien senior du content marketing SEO ; le billet est un retour d'expérience personnel (*« How I do… »*) publié sur le **blog Ahrefs** (ahrefs.com/blog) le **28 avril 2026**.
FinOps for AI Agents: A Four-Step Allocation Framework for Coding Assistant Costs (Claude Code, Cursor, Copilot) and Why Traditional Cloud Tagging Fails - Finout
Andrew Ng's editorial in The Batch #350 sets out an **acceleration hierarchy for coding agents** by type of software work: **Frontend (max) > Backend (moderate) > Infrastructure (low) > Research (minimal)**. The rationale rests on implicit *verifiability* (fluency in TypeScript/JavaScript plus an autonomous agent–browser test loop on the frontend) and on the LLMs' blind spots (corner cases / security / DB migrations for backend, opaque network tradeoffs for infra, irreducible hypothesis formation for research). The issue is rounded out by 4 structuring news items: **GLM-5.1 (Z.ai)**, a 754B/40B-active-parameter MIT-licensed model capable of autonomous tasks lasting 8 hours (SWE-Bench Pro leader at 58.4%); **Digit (Agility Robotics) at Schaeffler**, the first industrial deployment of humanoids (5'9"/143lb, $10–25/h vs $20/h for a human); the **anti-data-center revolt** (~$64B blocked May 2024 – March 2025, Maine moratorium on 20MW+ facilities, molotov cocktail at Sam Altman's home); and the **"assistant axis"** (Christina Lu, MATS / Oxford / Anthropic), which reduces persona drift and jailbreaks (Qwen3 32B: 83%→41%; Llama 3.3 70B: 65%→33%) without degrading IFEval/GSM8k/MMLU-Pro/EQ-Bench.
#Andrew Ng#The Batch#DeepLearning.AI
Andrew Ng (édito principal — fondateur DeepLearning.AI, Stanford, ex-Google Brain, ex-Baidu) ; rédaction The Batch (DeepLearning.AI) pour les sections actualités
Les Echos (Florian Dèbes) report from San Francisco: AI agents already integrated as colleagues in start-ups, "petri dish" (Aaron Levie / Box), Claude reflex before every meeting, personal Jarvis, 5 parallel agent tabs, "the limiting factor is human cognition" (Patrick Joubert / Rippletide), "brain fry" / cognitive overheating, BCG/HBR study putting 14% of employees overwhelmed, "token-max" ranking mode for the biggest AI users, testimonials from Sinaï/Bangay/Allali/Hodjat/Pantera/Chapeau and an echo of Siddhant Khare ("AI reduces production costs but increases coordination costs").
#Silicon Valley#San Francisco#AI agents as colleagues
Florian Dèbes (Les Echos, rubrique Travailler mieux / Vie au travail)
Revamp of the engineering hiring process at Sierra in the age of coding agents: AI-native onsite interview (Plan/Build/Review), removal of the algorithmic coding test, replacement of the phone screen with a system design interview, pilot of a debugging interview on an existing codebase.
Joint **DORA × delta** report (Google Cloud Professional Services), 60 pages, version **v. 2026.1** (citations February 2026, PDF created April 21, 2026), license **CC BY-NC-SA 4.0** — the first official **DORA ROI** framework dedicated to AI in the SDLC, with an **interactive calculator** at dora.dev/ai/roi/calculator. Pivotal thesis: ***"AI is an amplifier"*** — AI **amplifies** simultaneously the strengths of high-performing organizations and the dysfunctions of struggling organizations; it does not create performance, it **multiplies it where it already exists**. New central concept: the ***J-Curve of AI value realization*** — every AI adoption goes through a **temporary productivity dip** (learning curve + verification tax + pipeline adaptation) before **exponential growth**, a metaphor for the *"tuition cost of transformation"* to be **explicitly budgeted**. Reference calculation: organization of 500 FTE / fully loaded salary $176k / 12.5% time saved per developer (≈ 1h/8h day) → **value $11.6M / investment $8.4M / ROI 39% / payback period 8 months (0.7 year)**. Modeled costs: licenses ($250/user/year), additional API ($80/user/year), training ($9,600/user/year), infra ($100k/year), J-Curve cost ($3.3M for a 15% drop over 3 months). Modeled value: **headcount reinvestment capacity** ($11M — freed capacity to reinvest, **NOT headcount reduction**), revenue from extra feature deployments ($990k, based on a 33% idea success rate, Larsen 2023), **negative downtime impact** (−$344k, "instability tax"). **Explicit reinvestment strategy**: ***"we strongly recommend organizations do not adopt a headcount-reduction strategy"*** — reinvest in innovation, retain talent, capitalize on institutional knowledge. Five pillars of value: Productivity / User Experience / Cost Efficiency / Developer Experience / Business Growth (from most direct to most indirect, *cumulated business value*). Five systemic keys of adoption: **Trust + Platform + Data + Users + Guardrails**. Two-phase roadmap: (1) **Build context layer (CapEx)** — quality IDP + healthy data ecosystems; (2) **Empower human in loop (OpEx)** — context engineering + trust in AI. Indicators: leading = experiment frequency + deployment frequency; stability gauge = change failure rate + rework. Three scenarios to model (Conservative 0.8 value × 1.5 cost / Realistic 1.0 / Optimistic 1.2 × 0.8). External data mobilized: 78% of executives report ROI on ≥1 gen AI use case (Google Cloud), 88% of early agentic AI adopters see positive ROI, **35-40% greenfield productivity vs ≤10% brownfield/legacy** (Stanford), inference cost ÷280 between Nov 2022 and Oct 2024 (Stanford AI Index 2025), **727% ROI over 3 years** for Google Cloud AI customers, average market AI payback of **8 months**. Acknowledged weaknesses: *"all models are wrong"* — the model needs contextualizing, the calculator needs adjusting; risk of double-counting value (time saved → both avoided hire AND extra revenue); a "loose" user experience link, hence excluded from the calculator. **Deontological insight**: ***"We don't measure AI by the code it writes but by the bottlenecks it clears"*** — measured by bottlenecks cleared, not code volume. **Major relevance** for CIOs/CTOs who need to build a defensible AI business case for a CFO/board; for France/Europe, to be articulated with Wescale (realistic X3-X4), Tatsyi/Raiffeisen Bank Ukraine (bank case study, −75 people but deliberate reinvestment), Frizzo (3-5× median), Curran/Intercom (3× R&D over 16 months), DORA Report 2025 (on which this ROI builds).
#DORA ROI of AI-assisted software development#Google Cloud DORA report 2026.1#J-Curve of AI value realization
Rapport conjoint **DORA team × delta team** (Google Cloud Professional Services). Auteurs principaux : **Eva Dong** (AI Value Realization Americas, ex-McKinsey 8 ans, Master Financial Engineering Michigan) · **Andre Ellis Jr.** (Cloud Financial Operations Lead, Morehouse + Wharton MBA) · **Nathen Harvey** (DORA team lead, co-auteur multiples DORA reports + 97 Things Every Cloud Engineer Should Know) · **Vivian Hu** (10X Technology Consultant, contributrice DORA 2025 State of AI-assisted Software Development) · **Ursula Lübbert-Passing PhD** (AI Value Realization EMEA, 20 ans benchmarking + value advisory, PhD effort estimation software projects) · **Eric Maxwell** (lead 10X Technology consulting, ex-Chef Software, contributeur DORA) · **Aaron Wanjala** (cloud developer advocate Spring Boot/Angular). Conseillers et contributeurs : **Ben Jose · Eric Lam · Matt Orr · Allison Park · Ryan J. Salva · Jerome Simms · Dave Stanke · Cedric Yao**. Design : Human After All (humanafterall.studio). Document publié sous licence **CC BY-NC-SA 4.0** · version v. 2026.1 · citations retrieved February 2026.
Synthesis by Addy Osmani (Google, Chrome/Cloud) of the emerging field of *harness engineering*: the equation `agent = model + harness`, the *ratchet* principle ("every mistake becomes a rule"), the HumanLayer "skill issue" reframe, Terminal Bench evidence (Top 30 → Top 5 from a harness change alone), the layered Claude Code architecture, Anthropic's "harnesses don't shrink, they move" vision, and Harness-as-a-Service (Claude Agent SDK, Codex SDK, OpenAI Agents SDK). Pivot article that consolidates Trivedy, HumanLayer, Anthropic, and Böckeler into a doctrine.
#harness engineering#agent harness#Addy Osmani
Addy Osmani (Software Engineer at Google, Cloud + Gemini)
Public update from Darragh Curran (R&D, Intercom) nine months after his commitment to double R&D productivity in 12 months through AI. Result: **3x achieved in 16 months, with no signs of plateauing**. Quantified data from a 500-person R&D organization / 8.5M lines of code: **93.6% of PRs are agent-driven**, **19.2% AI-approved** (target >50%), cost/PR **-50%**, defect backlog **-54%**, time-to-shipping **-39%**, breaking-changes downtime **-35%**, top 5% of performers at **6x the median PR throughput**, **497 autonomous PRs** in the first 4 weeks, **153 contributors / 267 specialized skills** in a private *Skills-Based Plugin Architecture*. Curran declares ***"All technical work is becoming agent-first. This is the top priority for R&D."*** Pivotal article of the *agent-first organization* dossier, comparable only to Stripe Minions and StrongDM in the 2026 corpus.
#Darragh Curran#Intercom#Fin Ideas
Darragh Curran (R&D leader, Intercom — publication via Fin Ideas, plateforme média Intercom).
FinOps for AI agents centered on "cost per outcome": why traditional FinOps fails against runtime behavior, guardrails, behavioral observability, and a 4-phase lifecycle - Orq.ai
Episode #351 of the French-language podcast **If This Then Dev** (Bruno) with **Julien Lépine**, Chief Technology Officer of **AWS France** (13 years at Amazon), recorded on the sidelines of the **AWS Summit Paris** (April 1, 2026, ~10,000 attendees). Pivot thesis: in the agentic era, writing code becomes secondary, and value shifts toward **understanding context, architectural trade-offs, and human accountability**. Central proof point: the **redevelopment of Amazon Bedrock** — a critical platform handling thousands of billions of requests — by a team of **6 people in 72 days** (vs. an estimated 30 people / 18 months), **code entirely generated by AI**, without vibe coding. AWS is **standardizing internally on Kiro** (IDE + CLI, running on Claude Sonnet/Opus) for ~30,000 developers (announced by Matt Garman at re:Invent). Throughline: **keeping control** without reviewing everything — via **formal modeling (TLA+)** and **Raisonnement automatisé** to prove invariants and bound agents, **blameless post-mortem**, and the principle that "responsibility for an agent's action rests with the person operating it." Emergence of the **AI DLC** (sprints → multiple daily **Bolts**) and the risk of **cognitive overload / burn-out**.
#AWS Summit Paris#Amazon Web Services#code agents
**Julien Lépine** — Directeur de la technologie (CTO) d'Amazon Web Services France · 13+ ans chez Amazon ; ses équipes accompagnent les clients AWS sur le cloud · la data et l'IA. **Hôte** : Bruno (créateur et animateur du podcast *If This Then Dev*).
Bain & Company brief (**April 2026**) (David Lipman, Greg Callahan, Daniel Goetz, George Sunderland — part 1/5 of the series *"software industry in the age of AI"*) analyzing the impact of AI on the **Rule of 40** (canonical SaaS metric: *growth rate + profit margin ≥ 40%*) and concluding on a **double pressure**: **headwinds** (slowing market growth + massive AI infrastructure costs) and **tailwinds** (AI productivity + 10-25% EBITDA transformation + outcome-based pricing). **Striking central data point**: a *marketing technology* client case — **AI costs multiplied by 3.49 (+349%) while revenue grew only 38%** over one year. **Pivot thesis**: SaaS leaders may have to ***"settle for the Rule of 30"*** temporarily to stay competitive against **AI-natives**, accepting short-term margin compression for long-term positioning. **Two explicit paths forward**: (1) ***Financialize*** — minimize AI investment, optimize cash, operate as a *"durable generator"* but limit future growth; (2) ***Invest to Grow*** — accept short-term margin pressure, reinvest aggressively in AI capabilities across product and operations. **Tailwinds in detail**: sales/marketing/R&D productivity, successful transformations = **+10-25% EBITDA**, future *outcome-based pricing* opportunity (revenue shifting from fixed seats to labor/operations economics), incumbents can leverage customer relationships and embedded workflows against AI-native challengers. **Headwinds in detail**: *"software penetration is topping out in some areas"* (market saturation), AI infrastructure + inference + model access introduce **significant variable costs into businesses that have historically had high margins**. **CFO/board signal**: the Rule of 40 itself, as a **stable norm**, is starting to shift; some players will temporarily fall outside this norm and **that is strategically rational**. **Major relevance** for B2B SaaS CFOs/CEOs/boards and PE/VC software investors evaluating their portfolios — the first quantified institutional benchmarking of the *protect margins / invest aggressively* dilemma in 2026. To be connected with: Bain **part 2/5 cross-system labor $100B** (2026-05), DORA ROI 2026 (financial framework), Wescale (realistic X3-X4), Tatsyi/Raiffeisen (bank −75 people), Curran/Intercom (3× R&D in 16 months), Menlo Ventures *State of Generative AI Enterprise* (2025-12-09).
#Bain & Company#Rule of 40#growth rate plus profit margin
**David Lipman · Greg Callahan · Daniel Goetz · George Sunderland** — partners et experts Bain & Company spécialistes industrie logicielle / SaaS / private equity software. Article publié en **avril 2026** sur bain.com/insights · **partie 1/5** d'une série Bain sur *"the software industry in the age of AI"*. La partie 2 (*The $100-Billion SaaS Opportunity Hiding in Cross-System Labor*, mai 2026) est dans le dossier de veille.