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

I find it interesting how Americans roll over open corruption now


Indeed, it escalated quite quickly to somewhat under the table in the first term, but the second term hadn't already started and it was all out in the open. With some discontent (especially around the comic depicting it that got denied by the Washington Post, resulting in their cartoonist leaving to publish it), but nothing near the outrage there should be.


Runable | ONSITE - Bangalore | Full Time | https://runable.com

Runable is building general purpose automation agent to automate anything digitally possible.

We are hiring for backend/platform focused full stack engineers, video editor and a community manager intern.

https://runable.notion.site/Careers-at-RUNABLE-20dfb5780e748...

Apply. We have a simple take home for engineering role unless you have a solid github or stuff you built we can check.

Task: Build a simple orchestrator that runs a coding agent in the background inside firecracker instances with novnc support.


I think providing examples and sample code is better than tying your API to AI sdk.

Due to how fast AI providers are iterating on their APIs, many features arrive weeks or months later to AI SDK (support for openai computer use is pending since forever for example).

I like the current API where you can wait for an event. Similar to that, it would be great to have an API for streaming and receiving messages and everything else is handled by the person so they could use AI sdk and stream the end response manually.


Pretty much was my first question if there was support for streaming events. Any way we could be beta tester? ༼ つ ◕_◕ ༽つ


100% shoot me a note at gabe [at] hatchet [dot] run and we can share some details here for the signatures that exist, but are going to change


There is no contrast. Wow! Why?


I check multiple different apps to order food or taxi services every day looking for cheapest price and availability. It’s a pain and I don’t like the decision fatigue.

I thought why not automate this and turn it into an app so I built this MCP server.

I’m not using vision at all (mostly a fallback) and parsing the accessibility tree into something LLM can understand.


That’s an insane amount of money. What is open AI cooking behind the scenes?


The books


Unrelated. What happened to your anime studio?


Thanks for checking in. :)

We're still working on controllable video diffusion tools for artists, and we've learned a lot. I posted a bit about it a couple of weeks ago:

https://news.ycombinator.com/item?id=43102395

We'll do a "Show HN" soon!


He seems to be of Indian origin. Indian households can be very tight knit and prioritize financial success a lot more.


Tight knit might be downplaying the hold mothers of the subcontinent tend to have over their children.


All the more reason why they need to hear the truth


Do you have deepseek r1 support? I need it for a current product I’m working on.


Indeed we do https://glama.ai/models/deepseek-r1

It is provided by DeepSeek and Avian.

I am also midway of enabling a third-provider (Nebius).

You can see all models/providers over at https://glama.ai/models

As another commenter in this tread said, we are just a 'frontend wrapper' around other people services. Therefore, it is not particularly difficult to add models that are already supported by other providers.

The benefit of using our wrapper is that you can use a single API key and you get one bill for all your AI bills, you don't need to hack together your own logic for routing requests between different providers, failovers, keeping track of their costs, worry what happens if a provider goes down, etc.

The market at the moment is hugely fragmented, with many providers unstable, constantly shifting prices, etc. The benefit of a router is that you don't need to worry about those things.


Yeah I am aware. I use open router at the moment but I find it lacks a good UX.


Open router is great.

They have a very solid infrastructure.

Scaling infrastructure to handle billions of tokens is no joke.

I believe they are approaching 1 trillion tokens per week.

Glama is way smaller. We only recently crossed 10bn tokens per day.

However, I have invested a lot more into UX/UI of that chat itself, i.e. while OpenRouter is entirely focused on API gateway (which is working for them), I am going for a hybrid approach.

The market is big enough for both projects to co-exist.


They are just selling a frontend wrapper on other people's services, so if someone else offers deepseek, I'm sure they will integrate it.


Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: