HN user

botusaurus

30 karma
Posts1
Comments32
View on HN

But NanoClaw isn't just my personal project anymore. Thousands of people are using it. People are running production workloads on it. Businesses are building on it. There's a real community now.

as OpenClaw and now NanoClaw became "enterprise", now we need a new FemtoClaw to pick up the indie/boutique place

langchain is stuck in innovator dilemma - it was built for gpt 3.5, or 4, it needs a different design for todays models, but cant evolve because of existing users and backward compatibility

just like jQuery still exists and is being actively developed

what about the interaction between these 2 flows:

- summarize email to text file

- send report to email

the issue is tracking that the first step didnt contaminate the second step, i dont see how you can solve this in a non-probabilistic works 99% of the time way

parent was talking about a different problem. to use your framing, how you ensure that in the email sent to the proper to/cc/bcc as you said there is no confidential information from another email that shouldnt be sent/forwarded to these to/cc/bcc

but how do you check that an email is being sent to #general, agents are very creative at escaping/encoding, they could even paraphrase the email in words

decades ago securesm OSes tracked the provenience of every byte (clean/dirty), to detect leaks, but it's hard if you want your agent to be useful

he says claude is the best model for a personal assistent, and that codex is the best model for coding

you didn't see because you dont follow peter on twitter. he talked for months now how codex is a better coder.

ok, your quote was over generalized, you meant "current LLM need..." and not "any conceivable LLM"

although the word "energy" does not appear on that page, not sure where you get the galaxy energy consumption from