Viewing profile — eugeneonai
eugeneonai
HN member- Joined
- Sun, Apr 26, 2026, 3:07 AM UTC
- HN karma
- 1
- Public activity
- 11 items
- HN profile
- View on Hacker News ↗
About eugeneonai
Building infrastructure for production LLM workloads. Background: distributed systems, quant. yevheny@tesseraai.io
Recent public activity
-
comment
Comment #48439255
[flagged]
-
comment
Comment #48409369
Great, will it be possible to see it in your profile?
-
comment
Comment #48398281
The 79% / 67% reduction generalizes broader than IaC. Any CLI agents shell out to (curl, jq, grep, kubectl, gh, psql) burns the same token tax — verbose JSON, free-form text output…
-
comment
Comment #48398237
[flagged]
-
comment
Comment #48398183
[flagged]
-
comment
Comment #48383722
Agree on RSS as the right shape — and worth adding the cost angle nobody's quantified here yet. Having an LLM read a 50KB HTML page is ~$0.03 of gpt-4o input. Polling 1000 sources …
-
comment
Comment #48383469
Looks nice. The README pitches model-per-task picking but doesn't say much about context management. In coding-agent loops the full system prompt + tool specs re-send on every step…
- story
-
comment
Comment #48360457
[flagged]
-
comment
Comment #48360330
I agree, but my situation is a little different. I try to squeeze my hobbies into the workweek, and it ends up happening after work. I work from 10 a.m. to 10 p.m., then pursue my …
-
comment
Comment #48360208
Now I'll know where to get new ideas. I'm off to school, guys. The most original things can truly be learned from people whose thinking isn't yet "proper" to adults. I've always th…