Hacker Newsnew | past | comments | ask | show | jobs | submit | more tonyhb's commentslogin

In the partnership model Waymo charges uber for the ride and Uber charges the customer.

The interesting thing is that uber loses money on every ride. Waymo charges Uber more than Uber charges the customer.

On Uber’s side, though, this is preferable to losing the entire ride. Uber loses much more slowly by controlling the distribution and losing a few dollars per ride than by losing the entire customer base with no revenue from these customers.


Was going to post about your company compliance space (which we use and love). That naming conflict is rough and it's the first thing I had in mind.


AFAIK, it's due to things like single frame construction and expensive + backlogged parts which you order directly from Tesla (as opposed to, eg, a drivetrain that may be made for 3 separate manufacturers).

Or, when you do have an accident it's typically more expensive to repair.


https://inngest.com and agentkit. disclaimer is I work on it.

Does all of the event stuff and state stuff for you. Plus the orchestration.


Big fan of Inngest! Most of http://glama.ai/mcp logic is built on top of Inngest.


There are only a few popular, promoted alternatives to NextJS right now (that I know of): Remix and TanStack. That is, if you're fully React focused, ofc. I dont see promoting Remix as a red flag.


Promoting it? No problem. But promoting something you profited from without disclosing it violates FCC rules for broadcasting. I would say influencers aren't technically broadcasting but they are in principle.


The framework itself is super low overhead. You can deploy this anywhere, and if you deploy to inngest.com the P99 latency of starting agents is sub-50ms (and you can also realtime stream steps, tools, or model responses to the browser).

One of the main differences is the DX — _how_ you define the agentic worklflows is far cleaner, so it's both faster to build and fast in production.


The main one is deterministic routing (https://agentkit.inngest.com/advanced-patterns/routing). Here's what that means:

Each agent builds up state via tool use. On each loop of the network, you inspect this state to figure out which agent to run next. You don't build DAGs or create odd graphs — you write regular code in a router.

Or, more generally:

* Each agent has a specific goal within a larger network. Several agents each working on smaller goals means easier prompt generation, testing, iteration, and a higher success rate.

* The network combines agents to achieve an overall objective, with shared state modified by each agent

* The network’s router inspects state and determines which agent should run next

* The network runs in a loop, calling the router on each iteration until all goals are met

* Agents run with updated conversation history and state on each loop iteration

Realistically the challenge with agents has classically been: how can I build something reliable, and how can this run in production reliably? These patterns are largely what we've seen work.


Thanks for explaining. But I guess I'm still not clear on how the work gets divvied up. Not tryin to be a hater - I'll have to give it a spin - but that part's a bit murky to me still.


This is really cool, and PlanetScale Metal looks really solid, too. Always a huge sucker for seeing latency huge latency drops on releases: https://planetscale.com/blog/upgrading-query-insights-to-met....


This is an LLM response if ever there was one.


Wgats your Point?


It looks like Agents are less about DAG workflows and fully autonomous "networks of agents", but more of a stateful network:

* A "network of agents" is a system of agents and tools

* That run and build up state (both "memory" and actual state via tool use)

* Which is then inspected when routing as a kind of "state machine".

* Routing should specify which agent (or agents, in parallel) to run next, via that state.

* Routing can also use other agents (routing agents) to figure out what to do next, instead of code.

We're codifying this with durable workflows in a prototypical library — AgentKit: https://github.com/inngest/agent-kit/ (docs: https://agentkit.inngest.com/overview).

It took less than a day to get a network of agents to correctly fix swebench-lite examples. It's super early, but very fun. One of the cool things is that this uses Inngest under the hood, so you get all of the classic durable execution/step function/tracing/o11y for free, but it's just regular code that you write.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: