Viewing profile — krawczstef
krawczstef
HN member- Joined
- Thu, Aug 11, 2011, 11:50 PM UTC
- HN karma
- 263
- Public activity
- 125 items
- HN profile
- View on Hacker News ↗
About krawczstef
Recent public activity
-
comment
Comment #48487852
FYI - Burr is designed with recursion in mind, i.e. the ability to kick off Burr within Burr. So you could have an action that is managing several Burr subgraphs... Or you write yo…
-
comment
Comment #48479654
yep - here's something cool an end user wrote with Burr - https://github.com/msradam/phoebe Burr just helps you, the engineer, to really control the primitives. Then adds some cool…
-
comment
Comment #48479595
no. more lower level.
-
comment
Comment #48479587
user contributed :)
-
comment
Comment #48479581
Cause I submitted it. Learning the Apache process and cranking on other things has been a slow process. But we've got some momentum and beginning more regular releases.
-
comment
Comment #44852917
I agree with this post. Otherwise the larger picture is that MCP is a land grab for building an eco-system around integrations to get access to data. Your LLM agent is not valuable…
-
comment
Comment #43006886
Unfortunately their blog doesn't have the example they have on x.com - https://x.com/ZyphraAI/status/1888996367923888341 - which I think is more illustrative.
- story
-
comment
Comment #42507301
your comment made me think I read it wrong, but it's not closed source, they're just moving to a source available license...
-
comment
Comment #42504374
yep, agreed. I think that's another way to view the current state of "GenAI" tooling (e.g. all those complicated frameworks that received $M in funding) and why things like https:/…
-
comment
Comment #42314730
+1 for vanilla code without LangChain.
-
comment
Comment #42303765
Interesting! I feel like this is a cross between https://github.com/dagworks-inc/burr (switch state for context) and https://github.com/Netflix/metaflow because the output of the "…
-
comment
Comment #42301691
This is reminiscent of themes brought up in https://news.ycombinator.com/item?id=42253735 and most famously in https://news.ycombinator.com/item?id=36645575 ...
- story
-
comment
Comment #42206771
Forgot to mention, on the roadmap we have pluggable executors, e.g. delegating parallelism to whole agents/subgraphs to systems like "ray". Would love to collaborate with folks if …
-
story
Show HN: Modeling parallel (and hierarchical) agents with Burr
Hi all, just showing a new construct in Burr (for more info on Burr see - https://news.ycombinator.com/item?id=39917364 ) for modeling agent / agentic parallelism. We think a "grap…
-
comment
Comment #42180308
Looks great. But being burned by other "abstractions", e.g. LangChain, I'm weary of the oversimplification. How are you not going to make those same mistakes?
-
comment
Comment #42174389
Does this compete with Minio?
-
comment
Comment #41450510
@staranjeet we should get you plugged in as part of persistence with https://github.com/dagworks-inc/burr !
-
comment
Comment #41440568
Yep. When I was designing https://github.com/dagworks-inc/hamilton part of the idea was to make it easy to understand what and where. That is, enable one to grep for function defin…
-
comment
Comment #41206417
Wow. Implemented pregel to run a 3 node graph... Jokes aside, that's an interesting thesis to have in there...
-
comment
Comment #41204182
Really? Can you point to code for that? To me it's just a way to describe a graph and execute it, exactly like https://github.com/dagworks-inc/burr (I'm an author).
- story
-
comment
Comment #40752138
Here's a blog post that I just pushed that doesn't use them at all - https://blog.dagworks.io/p/building-a-conversational-graphdb (we have more on our blog - search for RAG). [disc…
-
comment
Comment #40473110
getting into enterprise is hard, so probably trying open source to help with that.