Viewing profile — vichoiglesias
vichoiglesias
HN member- Joined
- Sat, Feb 08, 2014, 3:24 AM UTC
- HN karma
- 3
- Public activity
- 14 items
- HN profile
- View on Hacker News ↗
About vichoiglesias
vichoiglesias.com vichoiglesias@hey.com
Recent public activity
-
comment
Comment #49107416
Got the iPhone Pro Max in beautiful orange... and could't get use to it. It feels heavier that the previous titanium versions, so sold it and got the Air. The lack of telephoto is …
-
comment
Comment #48885004
I always had this idea after reading so much about Lisp that I was designed for AI, but kinda forgot about it with all the craziness of the last years. When I read on the article t…
-
comment
Comment #48532428
Yes, exactly! I want to explore if ai workflows can be treated like unix treated programs, small composable transformations over artifacts.
-
comment
Comment #48531889
I’m working on Kern, a small, git native, make and unix inspired llm workflow. Modules are simply folders, and the tool just reads from stdio and outputs to stdout. Runs are stored…
-
comment
Comment #48396698
I think we are all experiencing more or less the same kind of pain regarding memory+llms, and love to see how different approaches exist this problem. How does mnemo decides when t…
- story
-
comment
Comment #47791095
I managed to run a council using OpenClaw twice a day of different models that would discuss my personal projects, and send me to telegram ideas or suggestions for the next steps. …
- story
- story
- story
-
comment
Comment #47171436
The self-extending part is wild! agent mutating its own tools mid-run makes trajectory fidelity even more make-or-break. On git hooks: checkpointing state is easy, but if replay is…
-
comment
Comment #47171212
When an autonomous agent fails at step 40, the bug was usually introduced at step 12. The hard part is finding it. Logs tell you what happened, but they don’t let you bisect a traj…
- story
- story