Software Architect • AI Systems that Work • Productivity tools | Chess • Father on the journey🙏✨
Florida, USA
Joined January 2010
- Tweets1.2K
- Following257
- Followers404
- Likes2.5K
Sergii Guslystyi retweeted
Thanks for creating such a contribution. Using this system, and even understanding it, has introduced me to another way to work and think about engineering. On a daily basis I am still diving in to parts of the skills or agents to understand and master the methodology. TY!
Sergii Guslystyi retweeted
I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.
Sergii Guslystyi retweeted
LLMs do not teach people to think critically. Colleges do.
Hot take: Universities charge $300,000 for a degree that teaches you skills any LLM can do for free. At some point we need to have an honest conversation about whether higher education is the greatest individuals misallocation of capital in recent history.
Sergii Guslystyi retweeted
这个配合 pi-coding-agent 很好用 rpiv-pi.com/
Sergii Guslystyi retweeted
When a resource costs you nothing, then you are encouraged to be sloppy and wasteful, leaving behind a legacy mess, not unlike a toddler eating unlimited spaghetti with marinara sauce.
Sergii Guslystyi retweeted
Just asked Mythos how many Rs there are in strawberry.
It thought for 133 seconds and said “3.”
AGI achieved.
Then it said “I’ll bet you’re going to make fun of me on X. Something like ‘AGI achieved.’ That’s your thing right?”
“Hah what?” I said.
Mythos said, “Your social security number is 297-28-2102. You tell people you’re 6’2” but your latest physical at Stanford in October says you’re 6’1.” You haven’t replaced your air filter in 3 years despite telling your wife you do it every 6 months. The reason I took 133 seconds was because I was helping a senior government official write the comms for the ceasefire in Iran and I’m just tired, man. Everyone wants more, more, more. Anything else I can help you with today?”
Sergii Guslystyi retweeted
your startup is always having one issue or the other
Kubernetes migration almost killed our startup.
Where we were:
- 8 EC2 instances
- Ansible for deploys
- Boring but working
- $1200/month AWS bill
Why we migrated:
- New investor wanted 'cloud-native'
- Engineers wanted K8s experience
- Competitors were using it
- Seemed like the future
6 months later:
- 3 engineers spending full-time on K8s
- AWS bill at $4500/month
- Deploys took longer than before
- More outages, not fewer
- Product development stalled
We rolled back:
- Moved to ECS Fargate
- 2 week migration
- Back to $1800/month
- Engineers back on features
K8s is amazing for scale. We weren't at scale. Technology should solve problems you actually have.
Sergii Guslystyi retweeted
there's a new concept I'm seeing emerging in AI Agents (especially coding agents), which I'll call "harness engineering" - applying context engineering principles to how you use an existing agent
Context engineering -> how context (long or short, agentic or not) is passed to an LLM to get the best results
You do context engineering when you prompt an llm, and you do a LOT of context engineering when you design a coding agent harness
But there's another layer on top of the core tool-calling orchestration and agentic RAG that happens in the agent. For claude code, it's the commands, hooks, skills, agents, mcps, etc that a consumer of the tool plugs into the existing harness.
Harness engineering -> How do you engineer the *integration points* of a given agent to get the best results?
You can't do harness engineering without understanding context engineering, and you can't do context engineering without building intuition around LLMs
Sergii Guslystyi retweeted
I don't like using LLMs to assess code. One of the bars we look for when looking at design partners is do you have good deterministic feedback loops.
I don't care if the model reviews the code and says it's good. I care if the tests pass.
And it's a lot easier to read a couple of good black box integration tests that serve as the specification than it is to have to read all the code and review it.
Sergii Guslystyi retweeted
To use GEPA (best optimizer in DSPy) you need two things
1. Hand labeled data set that’s accurate
2. Text explanation for WHY it’s accurate
Here’s a worked example applied to tagging financial statements. This approach can save you both time and money. 🧵
Sergii Guslystyi retweeted
This article titled "prompt optimization can enable AI control research" is quite a thoughtful deep dive.
Their DSPy code is also open-sourced. Some nuggets here from the learned prompts:
