Viewing profile — sparacha
sparacha
HN member- Joined
- Mon, Jul 01, 2024, 11:25 PM UTC
- HN karma
- 18
- Public activity
- 56 items
- HN profile
- View on Hacker News ↗
About sparacha
No profile information was provided.
Recent public activity
-
story
Show HN: Signals – finding the most informative agent traces without LLM judges
Hey HN Salman, Shuguang and Adil here from Katanemo Labs (a DigitalOcean company). Wanted to introduce our latest research on agentic systems called Signals. If you've been buildin…
-
story
Show HN: Preference-aware routing for OpenClaw via Plano
Hey HN! OpenClaw is notorious about its token usage, and for many the price of Opus 4.6 can be cost prohibitive for personal projects. The usual workaround is “just switch to a che…
- story
- story
- story
- story
-
comment
Comment #45455933
Hi HN — we’re the team behind Arch-Router [1], A 1.5B preference-aligned LLM router that guides model selection by matching queries to user-defined domains (e.g., travel) or action…
- story
-
comment
Comment #44772050
Hey! I built this. AMA. The model router is built into the proxy layer here: https://github.com/katanemo/archgw
-
comment
Comment #44652881
But you can also use tokens to implement routing decisions in a proxy. You can make RBAC natively available to all agents outside code. The incremental feature work in code vs an o…
-
comment
Comment #44651074
There is liteLLM, OpenRouter, Arch (although that’s an edge/service proxy for agents) and now this. We all need a new problem to solve
-
comment
Comment #44546887
That’s an example of what the edge component could do. Did you give the preference-based automatic routing a try?
- story
-
comment
Comment #44439016
RouteLLM is essentially a benchmark-driven approach. Their framework chooses between a weak and a strong model and helps developers optimize for a metric called APGR (Average Perfo…
-
comment
Comment #44438708
https://news.ycombinator.com/item?id=44436031
-
comment
Comment #44438547
Arch is developer friendly, but designed for enterprise-grade customers in mind. The core contributors of Envoy redesigned the proxy substrate to handle prompts - offering somethin…
-
comment
Comment #44438150
Overall performance degrades from 93.17 -> 92.99 with a quantized version
-
comment
Comment #44438075
Can you share more about your evaluation setup? I would love to see the specific usage pattern as we have tested our model against smaller LLMs and foundational models and our resu…
-
comment
Comment #44437364
yes - we have already published a quantized version here: https://huggingface.co/katanemo/Arch-Router-1.5B.gguf . The performance difference with a quant version is negligible. I'l…
-
comment
Comment #44436070
Hi HN! I am one of the co-authors of the paper. If there are any questions about our approach, I would love to answer them.
- story
- story
- story
- story
-
comment
Comment #43731567
good one!