Dreams
It is March 14, 2023; and the first 10x coder is released to everyone (GPT-4).
Engineers quit day jobs with:
Oh wow, now I can finally build out my side hustle! ๐
Certainly times of high hopes for the future
Setup
Software is in many ways similar to real world construction projects. It requires different experts, coordination, it always takes longer than expected and it is delivered with bugs.
So lets use the metaphore of "building a cabin" to "building a side-project", and how GPT is really making you into a fast sub-contractor.
Project Hopes
- I always wanted to build a cabin (aka side-project)
- BUT I was only a framer (aka backend engineer);
- NOW finally I can do everything and FAST (with gpt4+/mistral/...):
Delivery hopes
As a sub-contractor for everything, I can do myself:
- plumbing (devops/infra),
- doors, windows (frontend),
- and screw it I can even make it feel nice (design).
SO LETS GO! ๐ช๐๏ธ๐ง
At the start, it was so exciting!
All previously annoying tasks suddenly felt so easy:
-
Need to parse an email from SES into a Python ORM?
np done in 30 seconds ๐ช
-
Dockerfile for your ffmpeg on python-alpine with AWS lambda?
here you go sir ๐
-
Some automated deploy orchestration?
Here is SAML code โธ๏ธ (what a shit choice)
-
Voice recording React component plugged into S3 for infinite size uploads?
Yeah lets go just hammer in prompts ๐
-
Create coherent design assets?
Sure thing ๐จ (but really my designer friends were like ๐คฆ)
-
Even could write Scala code with Monix! ๐คฏ
OMG YEAH (Scala only really for people with passion)
If you build it, they will come
Fast forward to 687 commits later: https://github.com/petercsiba/dumpsheet
I was wrong.
Just because you CAN it doesn't mean that you SHOULD.
Yes, I have built the cabin in record time, but it was beyond arctic cycle with custom heating involving ice fusion.
Reflecting, it was like my 7 year old self who just learned to code; I was again so so caught up in this artistic builder passion that I have completely forgotten about:
- customers
- existing tooling
Learnings
Chasing features instead of solving problems.
I felt like a ML algorithm over-fitting to a particular feature set. The product ended up so complicated, so specific that I couldn't even explain it.
Nah, now I can just build over buy every-time ๐ฐ
In the build vs re-use I often felt like:
Why should I integrate with say Langchain if I can build a super-custom agent chain with async python in a few hours?
WELL, cause it ended up shittier, with more code leading to more bugs while loosing opportunity cost.
So if you would do it again?
Go slow, Focus, Talk to people, Talk to customers, Talk to experts and only build 10x speed when it is new logic.
Silver lining: If you build it 10x faster
You will also learn your lesson 10x faster!
Top comments (4)
Hi Peter. Great talk.
As a "GPT Coder" myself I can relate.
I Blitz through several projects in a day just to build my portfolio and it felt great. It still feels great.
Artificial intelligence is a great tool but as a **beginner **it's best not to let it get to your head.
Cannot agree more fella! I think I pushed the GPT coders pretty far, but lost the sights of real people while doing so. Lesson learned!
My friend summarized this learning even better:
Hi Peter, thanks for sharing about voice agents! We're thrilled to introduce TEN๏ผgithub.com/TEN-framework/TEN-Agent๏ผ, the world's first real-time multimodal agent framework for next-gen AI agents. It's open-source and lets developers build agents with voice, video, and more in real-time. We'd love your feedback, and if there's anything we can do to make TEN more accessible, just let us know!