
Ez.-
396 posts

Ez.-
@ecura
Passionate for performance engineering.


I keep thinking I miss having someone like Steve Jobs in the industry. He had some standards. He cared about quality, coherence, and making great products. He could be ruthless and he had plenty of flaws, but it still felt like he and Apple were trying to make something genuinely great above all else. They had their opinions and you could respect that. They didn't try to force you, but make their case why they think it's good. Now tech feels driven by trend chasing, fear, scale, revenue comparisons, endless games and everyone talks their book. Investors come first, business goals next, and users last if not at all. I wish there would still someone like Steve still around

wtf




I keep thinking I miss having someone like Steve Jobs in the industry. He had some standards. He cared about quality, coherence, and making great products. He could be ruthless and he had plenty of flaws, but it still felt like he and Apple were trying to make something genuinely great above all else. They had their opinions and you could respect that. They didn't try to force you, but make their case why they think it's good. Now tech feels driven by trend chasing, fear, scale, revenue comparisons, endless games and everyone talks their book. Investors come first, business goals next, and users last if not at all. I wish there would still someone like Steve still around







We're bringing the advisor strategy to the Claude Platform. Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.

Pair Opus with GPT5.4 and Gemini 3.1 and experience superintelligence


The new Anthropic managed agents API is basically the Letta API that we've had since a year ago, but closed source and with provider lock-in. They even have read-only memory blocks and memory block sharing -- something which was unique to the Letta agents for a long time. Funny enough, we actually don't think this is the direction agents are going to go. Having API interfaces for memory blocks and tools is certainly convenient - you can spin up stateful agents as API services with just a few lines of code. But its also limiting: LLMs today are extremely adept at computer-use, and representing their memories in this way limits the action space of agents and their ability to learn. It's important to remember that just because something comes out of a frontier lab, doesn't mean its the "right" answer long-term. The Letta API ~1 year ago was somewhat of an antipattern in a sea of agent framework libraries offered by every lab. But now, stateful agent APIs are becoming the new norm - especially as providers try to lock in memory/state into their platforms to increase switching costs (which is exactly why we believe memory should live outside of model providers) If you want to see what the future is going to look like, follow @Letta_AI









