2ero_wf

Re:Muse: Meta's personal AI agent, features and capabilities on Thursday September 10, 2026 @01:13AM (#49638697)

Tried it, it's not designed by someone who need the software. tech is solid.

As a busy professional, i hate repeated shit work, kids' extra currilulum sign up, lunch order; insurance calls; things i don't want to do but have to do;

buying sneakers or good piece of steak actually are relaxing activity for myself.

there are some very common shitful painful things people want automated, but the app did none of them.

Re:Muse: Meta's personal AI agent, features and capabilities on Thursday September 10, 2026 @12:41AM (#49638491)

any expert knows their harness design? browser activity is long and isolated task ( potentially a subagent? )

it's known hard to surface subagent HITL back to main agent seamlessly. how is that done?

Ask HN: Do you need go-to-market strategy at early stage?

Posted by 2ero_wf on Tuesday June 09, 2026 @01:27AM
from the ask-hn dept.

My startup is pre-revenue. Last week i was in one of the local AI Startup meet up, and attended some GTM office hours hosted by some folks from big company marketing team.Was told Go to market strategy is necessary, need professional helps, it will guide how i run growth campaigns(cold emailing), branding(color). and that i am not able to aquire customer maybe because i don't have a...

( Read More... | 4 comments | on HN )

Re:Ask HN: How do you choose a model for a task? on Tuesday May 12, 2026 @06:06PM (#48115231)

Sonnet 4.6 for coding, some initial research Deepseek(V4 pro, R1) for building actual product keyword search/summary, cheap model like deepseek v4-flash ( i'd do this if i know the task needs 0 reasoning )

other models are mostly for cross-validation

Re:Ask HN: Which LLM are you using to evaluate your ideas? on Tuesday May 12, 2026 @03:03PM (#48112819)

I use Claude for initial validation. Then move to deepseek my stack is langchain, complexity sucks, but once you setup the skills, claude.md, AI is ok dealing with it, langchain makes it easy to switch LLMs. some minor issues here and there, e.g. different models have different messaging format.

so far so good.