My heuristic is that any diff an agent generates over ~1500 lines is too big and is indicative that the problem needs to be decomposed. This is my general pattern now for feature work:
1. Try to implement the whole feature, loosely guided. I call this the "draw the owl" prompt in reference to the meme. Expect garbage, you're going to get garbage.
2. If the diff is less than 1500 lines, review it and iterate normally. If the diff is more than 1500 lines, prompt the agent to decompose the problem into atomic, incremental, reviewable tasks. Simultaneously, do this yourself.
3. Agents will very often make these tasks way too specific to the shape they solved. You need to massage it into the right general shape. Do that.
4. Kick off new agents to work on those incremental things (as parallelized as possible). Apply the same rules.
5. At a certain, point, repeat the "draw the owl" prompt. At some point, you will get beneath your review-ability threshold.
This has been producing consistently high quality, maintainable, reviewable chunks of code that have a good handoff to either merge as-is or human refinement.
And with the latest frontier models at xhigh thinking, these are all slow enough that you can usually have multiple going concurrently while you are actively reviewing others or working on your own tasks.
HITL (human-in-the-loop) agents are still super important, especially for feature work. Features touch the human boundary in terms of UI, API, etc. And net new stuff can introduce pathologies in the architecture that violate desired invariants (these should be represented in specs or tests but we aren't perfect!).
I know a lot of the leading edge agentic discourse is about "loops" and agents driving agents continuously. I do some of that (will report on that later). But, in terms of raw daily get-shit-done type of work, this is my most rewarding pattern at the moment.
One of the new, buzzy jobs in Silicon Valley is the AI Forward Deployed Engineer (FDE), an engineer who is embedded within a client organization to help customize solutions, such as building and tuning agentic workflows that suit the clientās particular needs. Iāve heard from people who are wondering anew about the FDE career path since OpenAI and Anthropic started building new teams to place FDEs within client organizations.
The rise of FDEs for AI workloads is one way AI is creating new jobs (and why the jobpolcalypse narrative of upcoming job market collapse is false -- there will be many AI and non-AI jobs). However, I believe there will be far more AI Engineer jobs than FDEs, as I explain below.
The FDE role was pioneered about two decades ago by Palantir, which sent engineers to government locations to work on secure, air-gapped networks. In addition to having good technical skills, FDEs need communication skills and sometimes business skills. For example, they may need to speak with clients to understand their needs, formulate a strategy to prioritize projects, explain complex technology, and respectfully push back if a client asks for something unrealistic. Theyāre enjoying a resurgence because of the amount of work involved in taking an off-the-shelf LLM and building it into a custom agentic workflow that fits particular business needs.
However, I believe the number of AI Engineer jobs will be far larger. A company might accept a few FDEs to be embedded within its organization. But most companies will want far more of their own employees working on their projects. While my organizations do hire FDEs, we hire far more AI Engineers! Also, a common client concern is that it is hard to find vendor-neutral FDEs ā they are, after all, there to deeply integrate a particular vendorās product into a company. In this moment when itās hard to predict which AI service will be the best one in a yearās time, optionality (the ability to pick whatever vendor turns out to fit best in the future) is very valuable. In contrast, letting FDEs tightly bind a companyās processes significantly reduces optionality.
Right now, I see surging demand for AI Engineers who can build software applications using AI software components (like LLM prompting, agentic frameworks, evals, etc.) and effectively use AI coding agents (like Claude Code, Codex, Antigravity CLI, and OpenCode). As the AI Engineer role matures, I expect it to fragment into more specialized roles, like the generic Software Engineer role from decades ago fragmented into frontend, backend, mobile, data engineering, devops, and so on.
What will be the future, specialized AI engineering roles? I donāt know. Perhaps there will be AI FDEs, LLMOps Engineers, Evals Engineers, AI Data Engineers, Harness Engineers, and other roles we donāt have names for yet. But for now, I see a lot of AI engineers who are generalists create a lot of value. Skilled AI Engineers are in very high demand! As our field continues to mature over the coming decade, I look forward to new specializations within AI Engineering that create even more job opportunities.
[Original text: The Batch newsletter]
There will be no AI jobpocalypse.
The story that AI will lead to massive unemployment is stoking unnecessary fear. AI ā like any other technology ā does affect jobs, but telling overblown stories of large-scale unemployment is irresponsible and damaging. Letās put a stop to it.
Iāve expressed skepticism about the jobpocalypse in previous posts. Iām glad to see that the popular press is now pushing back on this narrative. The image below features some recent headlines.
Software engineering is the sector most affected by AI tools, as coding agents race ahead. Yet hiring of software engineers remains strong! So while there are examples of AI taking away jobs, the trends strongly suggest the net job creation is vastly greater than the job destruction ā just like earlier waves of technology. Further, despite all the exciting progress in AI, the U.S. unemployment rate remains a healthy 4.3%.
Why is the AI jobpocalypse narrative so popular? For one thing, frontier AI labs have a strong incentive to tell stories that make AI technology sound more powerful. At their most extreme, they promote science-fiction scenarios of AI ātaking overā and causing human extinction. If a technology can replace many employees, surely that technology must be very valuable!
Also, a lot of SaaS software companies charge around $100-$1000 per user/year. But if an AI company can replace an employee who makes $100,000 ā or make them 50% more productive ā then charging even $10,000 starts to look reasonable. By anchoring not to typical SaaS prices but to salaries of employees, AI companies can charge a lot more.
Additionally, businesses have a strong incentive to talk about layoffs as if they were caused by AI. After all, talking about how theyāre using AI to be far more productive with fewer staff makes them look smart. This is a better message than admitting they overhired during the pandemic when capital was abundant due to low interest rates and a massive government financial stimulus.
To be clear, I recognize that AI is causing a lot of peopleās work to change. This is hard. This is stressful. (And to some, it can be fun.) I empathize with everyone affected. At the same time, this is very different from predicting a collapse of the job market.
Societies are capable of telling themselves stories for years that have little basis in reality and lead to poor society-wide decision making. For example, fears over nuclear plant safety led to under-investment in nuclear power. Fears of the āpopulation bombā in the 1960s led countries to implement harsh policies to reduce their populations. And worries about dietary fat led governments to promote unhealthy high-sugar diets for decades.
Now that mainstream media is openly skeptical about the jobpocalypse, I hope these stories will start to lose their teeth (much like fears of AI-driven human extinction have).
Contrary to the predictions of an AI jobpocalypse, I predict the opposite: There will be an AI jobapalooza! AI will lead to a lot more good AI engineering jobs, and Iām also optimistic about the future of the overall job market. What AI engineers do will be different from traditional software engineering, and many of these jobs will be in businesses other than traditional large employers of developers. In non-AI roles, too, the skills needed will change because of AI. That makes this a good time to encourage more people to become proficient in AI, and make sure theyāre ready for the different but plentiful jobs of the future!
[Original text in The Batch newsletter.]
"Gartner predicts that by next year, half of the companies that fired workers for AI are going to hire them back. Also, 9 months ago, Microsoft proudly proclaimed that 30% of their code was written by AI, and since then, we've seen some of the worst software issues at the company in its
history."
This video is well worth watching. It's a balanced, real-world look at the effectiveness of AI (across many disciplines, not just software dev) and its impact on work, substantiated by a well-designed study that actually compares UI to human workers.
https://t.co/aKCbAGejz6
Hai mai pensato che la storia di una cittĆ millenaria come Tokyo potesse offrire spunti per progettare architetture software moderne e resilienti? https://t.co/l10ax6oeb5
At @Google, we are moving from a writingāfirst culture to a buildingāfirst one.
Writing was a proxy for clear thinking, optimized for scarce eng resources and long dev cycles - you had to get it right before you built.
Now, when time to vibe-code prototype ā time to write PRD, PMs can SHOW not tell. Role profiles are blurring, creativity and building are happening in parallel.
La complessitĆ ĆØ il nemico silenzioso del buon software.
John Ousterhout, in A Philosophy of Software Design, ci mostra come combatterla.
Ho rivisto la sua intervista con Gergely Orosz (The Pragmatic Engineer) qui š https://t.co/4vuBPo3zXu
Last week I completed the course Learning How to Learn. It inspired a new 3-part series I just launched on my newsletter Streams: Leading Teams that Learn https://t.co/WlxDAujubc
Feeling lost despite having it all? This thought-provoking piece explores the paradox of wealth and purpose. A must-read for anyone seeking meaning beyond material success https://t.co/u56IA2QL47
This morning, we published the Root Cause Analysis (RCA) detailing the findings, mitigations and technical details of the July 19, 2024, Channel File 291 incident. We apologize unreservedly and will use the lessons learned from this incident to become more resilient and better serve our customers. To any customer still affected, please know we will not rest until all systems are restored.
For the executive summary and full RCA, please visit https://t.co/VxZdW6gKmt
Being a lifelong learner isnāt about taking pride in your knowledge. It's about having the humility to know what you donāt know.
My top 23 insights from 2023 š§µ
@IKEAITALIA sto provando a prenotare da qualche giorno un appuntamento con voi, ma si presenta sempre questo errore. Al telefono mi avete detto di riprovare, ma niente. Mi dareste una mano?