iamtherhino

Thanks for the feedback-- I can say emphatically, that's not our intention in the least. We chose a lightning bolt to evoke speed, i.e., the "hyper" in Hypermode. I've asked design to take another look at the "H" logo.

updated our python example too!

I haven't seen one yet-- no reason we couldn't do that with Hypermode. I'll do some exploration!

I really like this approach.

I think there's a big advantage to be had for folks brining "old school" ML approaches to LLMs. We've been spending a lot of time looking at the expert systems from the 90s.

Another one we've been looking at is applying some query planning approaches to these systems to see if we can pull responses from cache instead of invoking the model again.

Obviously there's a lot of complexity to identifying where we could apply some smaller ML models or cache-- but it's been a really fun exploration.

That's a good idea-- then give them a link to "replay last X inferences with model ABC" so they can do a quick eyeball eval.

We've been playing with that in the background. I can try to shoot you a preview in a few weeks. It works pretty well for reasoning tasks/NLP workloads but for workloads that need a "correct" answer, it's really tough to maintain accuracy when swapping models.

What we've seen most successful is making recommendations in the agent creation process for a given tool/workload and then leaving them somewhat static after creation.

Not at all! I'm updating the banner now

Signups are open: hypermode.com/sign-up

There's a waitlist for our prompt to agent product in the banner. That's a good call to update it to be more clear.

Hey! Co-founder of Hypermode here.

Agreed on swapping models for code-gen doesn't make sense. We're mostly indexed on GPT-4.1 for our AgentBuilder product. I haven't found it easy to move between models for code super effective.

The most popular use case we've seen from folks is on the iteration/experimentation phase of building an agent/tool. We made ModelRouter originally as an internal service for our "prompt to agent" product, where folks are trying a few dozen models/MCPs/tools/data/etc really quickly as they try to find a local maximum for some automation or job.

Hi Folks -- I'm one of the people who worked on this project along with the rest of Hypermode team. Happy to answer questions or hear your feedback!

Companies are starting with OpenAI, etc. to build version 1.0 of their apps then have to rewrite to use a smaller, more specialized model to improve outputs or improve costs.

Vercel/ZEIT is typically a bit cheaper in the long run for popular sites with the fixed costs. If your traffic is really light, then Netlify probably is.

If deploying a Next.js site, it makes sense to deploy on top of the platform made for it (ZEIT/Vercel)

The primary driver here is moving from a hosting company to a workflow/developer productivity company. If you're using ZEIT for staging/test deployment previews or hosting SSG or hybrid SSR/SSG Next.js it all pencils out nicely. It definitely doesn't work for the original container-first model.

Workato does a really good of integration recipies for known use cases. Time to value is really short with them.

Tray does a really good job as a general purpose automation platform. It’s really extensible and allows technical users to pull the covers off and do a lot more and semi-technical business users to get by without code.

At a high level: I’d go with workato if I had an acute problem that I needed fixed quickly. I’d go with tray if I saw automation being a long term strategy at my company where I know I’m going to need lots of flexibility integrating legacy applications with SaaS, etc.

At Neo4j, We're always looking for great CS undergrads to join our developer relations engineering team for the summer.

neo4j.com

devrel at neo4j dot com

I think you dropped a 0.

0.13*31BN = ~$4BN, still a 10X return if they've invested $400M.

Here's one using Neo4j (graph databse): https://neo4j.com/developer/graphql/

Most enterprise database vendors now charge on a "per-core" basis. There are some OLAP / NoSQL vendors that are moving to a per XX GB Ram model.

We see Neo4j get used relatively frequently as the aggregate view of data pipelines, e.g., Roam Analytics uses Neo4j to spit out tables/views across many different data sources to perform ML enrichment on that they then pipe back into the graph to feed their app.

eBay (ShopBot) is a Neo4j powered ML chatbot. AirBnb also builds knowledge graphs with Neo4j.

Video from GraphConnect today talking about knowledge graphs: https://youtu.be/dqrlotzdUlo?t=3175

Transparency: I'm an employee at Neo4j.