Viewing profile — rchaves

Hello HN! tl;dr: We built Scenario, an open-source testing library for AI agents. It simulates real conversations with your agent, its code-driven, and lets you assert anything mid…

well I think hype is not bad per se, I'd do it even if not trying to make a buck, it's okay (up to a point) to hype up something so that eventually it finds a problem where it fits…

same here, but I would even avoid "strong arguments" because that's what we all have been doing so far what I want is real use cases, show me real-world production examples from es…

is this multi-agent collaboration though, or is it just a workflow? All examples you listed seem to have pretty deterministic control flows (write then validade, context exceeded, …

Nah it's just a marketing problem, "GPT" and "ChatGPT" names is the biggest asset OpenAI has, people have expectations so high for GPT-5 that they cannot burn this name unless it's…

From @lateinteraction on twitter: In so many ways, good and bad, (LLM-based) Agents are the new object-oriented programming. Part of it is that: there's nothing that you can't do w…

Erm, he wrote the article with “you” to invoke the feeling of the reader thinking about their own use case, which I did Different because I ran without good practices before, got m…

Yes exactly, from the experience he had as Facebook massively scaling up, while all good practices were thrown down the window (except for foundation and critical parts) and extrem…

I’ve seen people spending 10 minutes to test things by hand, would have taken them less to write and run a test, specially with AI now When writing test actually makes it faster to…

Not true. Kent Back’s 3X is a much better take, test and good practices for what is high risk and hard to change, move fast for most of it on the rest to try to find that black swa…

yeah I guess base models without built-it CoT are not going away, exactly because you might want to tune it yourself. If DSPy (or similar) evolves to allow the same or similar than…

Nope, the trains are not often late, this is just in Germany

If you look closely it actually does give multiple instructions per screenshot! However it cannot get too far, because the screen changes under it. For example when it starts typin…