---
date: "2023-08-27T09:58:08.000Z"
title: "2023-08-27"
tags: ["temporal","python","language_models"]
draft: false
---

It's much easier to test Temporal Workflow in Python by invoking the contents of the individual Activities first, in the shell or via a separate script, then composing them into a Workflow.
I need to see if there's a better way to surface exceptions and failures through Temporal directly to make the feedback loop faster.

---

import { Tweet } from 'astro-embed';

From [this paper](https://arxiv.org/abs/2308.10335):

> 62% of the generated code contains API misuses, which would cause unexpected consequences if the code is introduced into real-world software

This work further reinforces some [recent thoughts](/logs/2023/08/22) on the importance of measuring the quality of a language model's output for a use case.

---

<Tweet
  theme="dark"
  id="https://twitter.com/Altimor/status/1695543062444015733"
/>

It had been a while since I thought about this 😬