Why I'm Betting Against AI Agents in 2025 (Despite Building Them)
Why I'm Betting Against AI Agents in 2025 (Despite Building Them)
utkarshkanwat.com
Why I'm Betting Against AI Agents in 2025 (Despite Building Them)
8 comments
-
-
Interesting. I have never seen the economic side of it being discussed outside of nvidia stock prices.
-
TL;DR: Three Hard Truths About AI Agents After building 12+ production systems, here's what I've learned: -Error rates compound exponentially in multi-step workflows. 95% reliability per step = 36% success over 20 steps. Production needs 99.9%+. Context windows create quadratic token costs. -Long conversations become prohibitively expensive at scale. -The real challenge isn't AI capabilities, it's designing tools and feedback systems that agents can actually use effectively.
The TL;DR of the TL;DR is compounding expensive, error-prone results.
-
It sounds like one should be building deliberate AI workflows with extra checks (automated or human in the loop) that make careful and cost efficient incremental progress toward a measurable goal.
Sounds like hard work... when we could just build 1,000,000 MCP servers instead. (raises pinkie to corner of mouth)
-
Much of the hype around AI is based on the hope that we will no longer need to organize our own thoughts, express our own perspective, or understand the details or our own lives. These people want some hyper generalized, disembodied 'intelligence' to do everything for them ... it's no wonder that that they produce little more than hot air.
-
-
-
I keep having the same question: would it benefit to have a separate agent whose job was to error-check the first agent?
-
The three stooges didn't seem any less likely to get into trouble despite their strength in numbers
-
-
Also... how many security vulnerabilities have those agents introduced?
8 comments
As someone who works in tech, currently testing AI integration into healthcare EHR- the current state of AI is simply not safe for anything outside transcription- and even that is error prone without strict re-reading (not scanning!) for error correction.
The errors can be subtle but life threatening. I highly recommended against integrating it - but the most lazy providers were already using AI illegally for their notes so this was seen as a middle road.
Medical care and provider training in the USA is not ok right now, and getting worse. AI and misinformation is accelerating the decline.