schlunker
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 3 days ago

Why I'm Betting Against AI Agents in 2025 (Despite Building Them)

utkarshkanwat.com

external-link
message-square
11
fedilink
13
external-link

Why I'm Betting Against AI Agents in 2025 (Despite Building Them)

utkarshkanwat.com

☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 3 days ago
message-square
11
fedilink
I've built 12+ production AI agent systems across development, DevOps, and data operations. Here's why the current hype around autonomous agents is mathematically impossible and what actually works in production.
  • queermunist she/her@lemmy.ml
    link
    fedilink
    arrow-up
    2
    ·
    2 days ago

    But doesn’t the LLM sometimes churn out tedious garbage that you have to fix, thus not actually saving time?

    • ☆ Yσɠƚԋσʂ ☆@lemmy.mlOP
      link
      fedilink
      arrow-up
      1
      ·
      2 days ago

      That’s where the rate of success becomes important. LLMs mostly produce decent code when applied to common cases like the examples I gave above. My experience is that vast majority of the time it’s as good as what you’d write, occasionally needing minor tweaks. However, there’s nothing forcing you to use the code they produce either. If the LLM stumbles, you can always fall back to writing the code by hand which leaves you no worse off than you would’ve been otherwise. It’s all about learning how the tool works and when to use it.

      • queermunist she/her@lemmy.ml
        link
        fedilink
        arrow-up
        1
        ·
        2 days ago

        You have to check it every single time, though, erasing any time savings. You’re saving effort, maybe, but not time.

        • ☆ Yσɠƚԋσʂ ☆@lemmy.mlOP
          link
          fedilink
          arrow-up
          1
          ·
          2 days ago

          You’re absolutely saving time, checking that the code works is far less time consuming than writing it. Especially for stuff like UIs or service endpoints. I literally work with this stuff on daily basis, and I would never go back. There’s also another aspect to it which is that I personally find it makes my workflow more enjoyable. It lets me focus on things I actually want to work on, while automating a lot of boilerplate that I had to write by hand previously. Even if it wasn’t saving me much time, there’s a quality of life improvement here.

          • queermunist she/her@lemmy.ml
            link
            fedilink
            arrow-up
            1
            ·
            2 days ago

            METR measured the speed of 16 developers working on complex software projects, both with and without AI assistance. After finishing their tasks, the developers estimated that access to AI had accelerated their work by 20% on average. In fact, the measurements showed that AI had slowed them down by about 20%.

            • ☆ Yσɠƚԋσʂ ☆@lemmy.mlOP
              link
              fedilink
              arrow-up
              1
              ·
              2 days ago

              Yes, I’ve seen this as well. First of all, 16 devs is a tiny sample, a far bigger study would be needed to get any meaningful results here. Second, it really depends on how experienced people are at using these tools. It took me a while to identify patterns that actually work repeatably and develop intuition for cases where the model is most likely to produce good results.

Technology@lemmy.ml

technology@lemmy.ml

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@lemmy.ml

This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.


Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.


Rules:

1: All Lemmy rules apply

2: Do not post low effort posts

3: NEVER post naziped*gore stuff

4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.

5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)

6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist

7: crypto related posts, unless essential, are disallowed

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 230 users / day
  • 490 users / week
  • 2.55K users / month
  • 7.86K users / 6 months
  • 1 local subscriber
  • 39K subscribers
  • 3.77K Posts
  • 48.9K Comments
  • Modlog
  • mods:
  • MinutePhrase@lemmy.ml
  • BE: 0.19.5
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org