1. Built an agent memory tool since all agents and clis are dumb and don't remember anything. Instead of prepping 300 project files and Md files I just say:
Check sugar memory for the latest thing we were working on.
2. The second thing is when making changes across a large codebase agents are also dumb at figuring this out and also grep 300 things, using tons of tokens. Instead I say
Check RemembrallMCP to analyze the impact of the change.
I understand what you're saying, but strictly speaking is it fair to say they aren't profitable? Didn't they along with other participants of LLM-race invest heavily into the infrastructure and the said infra wasn't yet delivered.
My understanding is that it's unreasonable to claim a hotel isn't profitable when they're still on the building stage.
I do understand that we don't have enough energy to turn it on when all of them are delivered, but that's a separate issue.
This has less to do with their balance sheet and more to do with the intent of the organization when it was founded. They were supposed to create open-source AI models and only let revenues influence the direction of the organization so much when weighed against the public good.
... but they did it in a place and culture filled with people who would probably sell their own mothers into slavery if they were allowed to provided it increased the valuation of their startup, so here we are.
Currently, we face lots of churn in our ecosystems. API updates, CVEs that need updates, supply chain compromises - keeping up is getting harder and we need something to help us manage that, get notified and allow us to take action.
This is why I created ChangeSpec, an open standard to communicate software changes.
I'd love to get feedback and work on it together, it's still early but I hope you like it.
reply