LangChain's co-founder: "memory can be a real moat." the architecture that builds this? four markdown files and a cron job. someone open sourced the full stack. memory layers, self-rewriting skills, a dream cycle that runs at 3am. yes, you should read every word of this.

I know we all grown. We talk about grown people stuff. Bills, kids, jobs, etc. What do you do for fun? What brings you joy? What do you when seek out a good time or wanna have fun?

Just a personal suggestion here, this paper is very deep into distributed systems like vector clocks, gossip protocol, raft etc... So if you don't know these concepts this can be pretty overwhelming, just like it was for me. But this was a personal take, feel free to explore it

some interesting trends in terms of LLM adoption 👀

Harness Engineering is the new Software Engineering

I agree with Aaron - I believe that IT services firms are going to flourish helping customers adopt AI.

>LangChain gives you testing tools. It never tells you what to test, in what order, or when you're done. This is changing soon Launching May 13th at Interrupt: interrupt.langchain.com

If you feel like Anthropic is going after every enterprise software market and that the big SaaS enterprise platforms like Salesforce, ServiceNow and Workday are toast, you are wrong. This simplistic thinking fundamentally misunderstands the difference between an AI Agent and

Some thoughts on the RLS discourse. If I'm building a multi-tenant online service backed by a database, I can choose from four basic architectural patterns: control-plane seperation, table-per-customer, explicit user info in schema, or fine-grained DB security features.

I’ve gone through the whole arc of 1. Omg AI can write code 2. Meh it makes mistakes 3. Omg Opus is AGI 4. No it still makes slop 5. Yes but everyone is still gonna use it like crazy And my view is these things need finer context. If Codex was told this is high

New sandbox!

System design concepts I’d master if I wanted to crush it. Bookmark this. 1.Consistent Hashing 2.Sharding 3.CAP Theorem 4.Quorum Consensus 5.Leader Election 6.Raft & Paxos 7.Gossip Protocol 8.Vector Clocks 9.Load Shedding 10.Circuit Breakers 11.Backpressure 12.Tail Latency

I told you guys. RL env = harness engineering = agentic coding = autoresearch. all are about eval/task design.

Good read to understand how debugging incidents happen at scale

Going from chatting all day with database orchestration engineers -> react devs is such a trip. Most of these people don't even know what a WAL is.

AI bois be like:

Red Hat's "harness engineering" paper argues the environment an AI works in matters as much as the weights: integrating telemetry, repos, and testing constraints into a single deterministic orchestrator measurably moves code generation reliability by 5%+. You cannot

How good engineers write bad code at big companies seangoedecke.com/bad-code-at-bi…

I'm now able to tell my agent “we are going to work on JIRA-1234” and it goes and pulls down the task, makes me a plan, I say yeah okay that looks good, and it generates the commit. I run an AI review from a different session, it finds 4 issues of varying priorities, I paste it

x.com/i/article/2047…