Tyler Cowen's recent talk on what will matter post AGI was really good. Buy: embodiment, physicality, charisma, looksmaxxing, taking the initiative Sell: writing, being a managerial elite, universities

Increasingly, I believe companies may need to be rebuilt from the ground up, where you have a single timeline of all observability product metrics file changes laid out in a retrievable system, like Datadog Posthog Google Drive Slack (really unified filesystem of Claude Code chats Codex chats). This might be the new data foundation for any and all companies to maximize AI. Needs to be rebuilt because keeping track of diffs on existing system basically impossible to produce longitudinal information on decisions and rollbacks, something coding agent storage companies are actively trying to figure out, but this should extend to businesses as a whole. Highly skeptical existing businesses will adopt this though because it means overhauling everything about their instrumentation and business data, but I think businesses built on this foundation probably can execute 100x better and faster

Increasingly, I believe companies may need to be rebuilt from the ground up, where you have a single timeline of all observability product metrics file changes laid out in a retrievable system, like Datadog Posthog Google Drive Slack (really unified filesystem of Claude Code chats Codex chats). This might be the new data foundation for any and all companies to maximize AI. Needs to be rebuilt because keeping track of diffs on existing system basically impossible to produce longitudinal information on decisions and rollbacks, something coding agent storage companies are actively trying to figure out, but this should extend to businesses as a whole. Highly skeptical existing businesses will adopt this though because it means overhauling everything about their instrumentation and business data, but I think businesses built on this foundation probably can execute 100x better and faster

i am having more fun than ever collaborating with people get an agent in the mix, we all bounce ideas off each other. prompt it, get more ideas. narrow in on something stop dooming about ai and your job and start gangprompting

making todo lists is the craziest life hack wow

if you’re still writing loops that prompt coding agents you’re falling behind. you need to build a meta agent that infers what loops you would have wanted based on your vibe and then write those loops

I want some kind of LLM workflow tool. • Ability to manage a set of input files (Markdown or similar), plus other general-purpose context. • With real-time collaboration. (And maybe some concept of snapshots or VCS integration.) • And the ability to create/manage a inference workflows and a stored set of prompts. • Access to general-purpose coding agents (and not just chat models). • Some concept of compiled outputs/inference results (which ideally can be shared externally). Many projects have this feeling: "there is all this stuff, which I want to process/compute over in this iterated way, with some build artifacts being important/worth saving." GNU Autotools x Notion or something. Is anyone building this?

billion-dollar company is the Vercel for internal agents. an employee writes a Claude Code agent, hits deploy, and gets hosting plus a Convex database in one click. IT scopes what it can touch, watches every execution, and tracks token spend per agent

Can we design legal agent verifiers that are up to 1,000x cheaper? Verifiers are LLM judges that check an agent’s work against rubric criteria: they're used both in agent benchmarking and as reward signal in post-training. But verifiers can be a bottleneck at scale. For example, our Legal Agent Benchmark (LAB), comprising 1,200 legal tasks across 24 different practice areas, requires grading an average of 50 rubric criteria per answer. We partnered with @LangChain Labs to design more efficient verifiers for LAB, comparing batch vs per-criterion scoring and open/cost-efficient models against Opus 4.7. The results were surprising: DeepSeek v4 Flash preserved much of the Opus 4.7 verifier signal with 94-96% agreement, between batch mode and per-criterion mode. This came with a massive reduction in cost: 18x cheaper on per-criterion verification, and ~1,000x cheaper on batch verification. In an RL setting with 3,200 rollouts, the cost of verification drops from $18,000 to $18.