37 points ltononro 1 hour ago 23 comments
anonzzzies 33 minutes ago | parent
realsarm 27 minutes ago | parent
bogdanoff_2 26 minutes ago | parent
ramraj07 6 minutes ago | parent
For example how langchain or whatever else handles subagents and deep research is laughable even today.
So whats the recommendation? Just use pydantic and code everything up yourself. Maybe strands I dont know.
infecto 26 minutes ago | parent
mawadev 25 minutes ago | parent
infecto 24 minutes ago | parent
simlevesque 15 minutes ago | parent
I use Apache Burr but it's not as good as LangChain. I just don't want to use software whose website has a pricing page if it's not a SAAS.
atonse 26 minutes ago | parent
Happy to be in such good company!
infecto 25 minutes ago | parent
quijoteuniv 23 minutes ago | parent
hek2sch 21 minutes ago | parent
adithyassekhar 18 minutes ago | parent
Bluestein 16 minutes ago | parent
dominotw 13 minutes ago | parent
Spotify built some nonsense like this too and made ridiculous claims that it saves 90 percent of tokens. I guess anything goes these days.
ianpurton 5 minutes ago | parent
wenbin 4 minutes ago | parent
seems every company that has spare engineering resource all builds such thing internally
olliebrkr 4 minutes ago | parent
lukebuehler 3 minutes ago | parent
I think this is where a lot of companies are going to go: on-prem platforms that give various teams access to agents that are as powerful as coding agents, but much more managed and governed.
I'm betting on this with my open source project, Lightspeed: https://github.com/smartcomputer-ai/lightspeed
olliebrkr 3 minutes ago | parent