Viewing profile — dchu17

Sorry, I may be misunderstanding the question. The way this works is that it stores workstreams and session state in a local SQLite DB, and links each ctx session to the exact loca…

that's interesting, I hadn't at this point but this sounds potentially useful

ctx is a local SQLite-backed skill for Claude Code and Codex that stores context as a persistent workstream that can be continued across agent sessions. Each workstream can contain…

Gave this a run and it was pretty intuitive. Good work!

Yes this is a major problem I thought about. The makeshift solution here was to redact the “identifying information” on the press release. Even then, I benchmarked that GPT-5 could…

Yes we know of a few. Honestly, it was pretty hard to even find a good catalyst calendar for this space. I'll give it a read to learn more. Thanks for the note!

That's interesting. I am curious, what kind of analyses did you work with on the molecule and drug itself? Was it like mostly reading papers/patents or did your team do anything ex…

Our initial goal with this project actually wasn't trying to get an edge in terms of better evaluating information, but rather, we wanted to see if an LLM can perform similarly to …

Hi HN, My friend and I have been experimenting with using LLMs to reason about biotech stocks. Unlike many other sectors, Biotech trading is largely event-driven: FDA decisions, cl…

Hi, thanks for the comment! Just wanted to respond to some of comments here: >> First, your business model isn't really clear, as what you've described so far sounds more like a re…

Yeah I think one of the things that would be interesting is to see how well it generalizes across tasks. It seems like the existence of pathology foundation models means there is c…

Thought about this too. I think there are two broad LLM capabilities here that are kind of currently tangled up in this eval: 1. Can an LLM navigate a slide effectively (i.e find a…

I've been thinking a bit more about better ways to build the tooling around it, I don't know much about video compression to be fully transparent but will read up on it. I have bee…

Nope I haven't, I can take a look and see if I can fit it in

I think so. It feels like there is more to be squeezed from just better prompts but was going to play around with fine-tuning Qwen3

Nope, I just did some prompt engineering on ootb models. I thought about doing some fine-tuning on like Qwen but think that there is still more performance to be squeezed out with …

> What's the performance of the models trained specifically on this task, and random guessing, compared to the expert pathologist? I should probably first clarify here, the disease…

Hey HN, this is David from Aluna (YC S24). We work with diagnostic labs to build datasets and evals for oncology tasks. I wanted to share a simple RL environment I built that gave …

Hi HN! This is David and Will from Fortress. Last month, we launched Fortress as a Postgres platform targeted at multi-tenant SaaS companies ( https://news.ycombinator.com/item?id=…

Yep! Just felt it wasn't for us. We originally built it for e-commerce as just a better way to get product data than through affiliate APIs but felt like most of the market pull we…

We really like Nile and it is definitely a company we look towards for inspiration! While we hope to share similar DXs, our fundamental difference is that we are focused on a BYOC-…

Thanks for the criticism! We still definitely need to work on our language to best communicate this; we'll work on keeping it more concise and straightforward to best highlight wha…

This is a great question :) We initially targeted startups at the moment that they are moving from a 3rd party DBaaS to databases on their own cloud. However, we just realized this…

This looks super interesting! Will check it out. Thanks for letting us know!

Thanks for the feedback! We've seen most SaaS companies use some sort of tenant_id column and this is definitely the most popular method that developers currently use. We want to p…