News · 2026-06-27

AI is learning a 'dark art' that even expert engineers struggle with

AI is beginning to learn radio-frequency integrated circuit design — a specialized chip engineering discipline long considered too reliant on intuition and unwritten craft to automate. According to reporting from IEEE Spectrum, AI systems are now absorbing the tacit knowledge that experienced RF engineers have built over careers, marking real progress into a domain practitioners openly call a "dark art."

Key facts

• What: Designing radio-frequency chips is so reliant on hard-won physical intuition that engineers call it a dark art - and now AI is starting to do it, a sign the automation frontier is moving into deep specialist craft.
• When: 2026-06-27
• Primary source: read the source

RF design differs fundamentally from ordinary digital chip design. Digital circuits are clean logic — ones and zeros governed by explicit rules. RF circuits operate in the analog world, where the physics is messy and unforgiving. At radio frequencies, tiny details carry outsized consequences: the exact length of a wire, the spacing between components, the way a signal at one spot leaks into another. Two layouts that look nearly identical can behave completely differently. There is no formula that takes a specification and returns a working design. Instead, expert engineers rely on years of accumulated feel — patterns internalized from thousands of designs, much of which they could not fully articulate if asked. That tacit, unwritten knowledge is what makes RF design a dark art, and what has made it so resistant to automation.

Automating ordinary digital design is like teaching a computer to follow a recipe — the steps are written down, so a machine can execute them. RF design is more like teaching a computer to cook the way a grandmother does, by taste and instinct, adjusting on the fly with knowledge she never wrote down and perhaps could not. For decades, that kind of know-how was assumed to be safe from automation precisely because it lives in human intuition rather than in any manual. What is new is that AI is beginning to absorb it anyway — learning the feel from data, the way it has learned other skills that resist explicit rules.

The significance extends well beyond one corner of chip engineering. Most public conversation about AI automation has focused on knowledge work that is already fairly explicit — writing, summarizing, coding, drafting. RF design is a different category: deep, specialized, physical engineering that experts themselves describe as more art than science. If AI can make real headway there, it suggests the automation frontier is not stopping at tasks we can spell out. It is moving toward tacit expertise — the accumulated craft that takes a human a career to build. Engineers discussing the story voiced exactly this worry and this hope: the same shift that could displace hard-won specialist jobs could also unlock designs and speed that human intuition alone never reached, and put scarce expertise within reach of teams that lack a veteran RF guru on staff.

How does an AI learn something nobody wrote down? The same way it learns most things it is not explicitly taught: from examples. Feed a model enough real designs — the layouts, the measured results, the tweaks that worked and the ones that did not — and it can begin to internalize the statistical regularities that experts feel but cannot articulate. The machine never reads a rulebook because there is not one; it absorbs the patterns directly from the record of what good designs look like, the way a chess engine learns winning positions without being handed a theory of chess. Pair that with the ability to rapidly simulate and test thousands of candidate layouts — far more than a human could try by hand — and the AI can search the messy design space in ways that complement, rather than copy, human intuition. That combination, learned feel plus brute-force search, is what makes a problem long thought too tacit to automate suddenly look approachable.

The honest caveat is to keep the scale in proportion. "AI learns the dark art" does not mean AI has replaced RF engineers or matched the best of them across the board. Learning to contribute to a hard design problem and learning to own it end-to-end are very different milestones, and the gap between an impressive assist and a trustworthy autonomous designer is wide — especially in a domain where a subtle physical mistake can sink an entire chip. What is genuinely notable is the direction of travel: AI reaching into a field long considered too intuition-soaked to touch. Whether RF design proves to be a one-off or the first of many "dark arts" to fall is the thing worth watching. For the bigger pattern of AI systems that plan and act in specialist domains, see AI agents.

Primary source, verified: read the paper →

Ground Truth. (2026, June 27). AI is learning a 'dark art' that even expert engineers struggle with. Ground Truth. https://groundtruth.day/news/ai-learns-the-dark-art-of-radio-chip-design.html

@misc{groundtruth:ai-learns-the-dark-art-of-radio-chip-design,
  title  = {AI is learning a 'dark art' that even expert engineers struggle with},
  author = {{Ground Truth}},
  year   = {2026},
  month  = {jun},
  url    = {https://groundtruth.day/news/ai-learns-the-dark-art-of-radio-chip-design.html}
}

Topics: hardware · chip-design · engineering · automation · industry