Plough_Jogger

Let's just change the title to "LLM coding agents don't use copy & paste or ask clarifying questions" and save everyone the click.

I have a feeling we will see a resurgence of some of the ideas around expert systems; current language models inherently cannot provide guarantees of correctness (unless e.g., entire facts are tokenized together, but this limits functionality significantly).

They forgot the "Testimonials" from fake customers.

My sense from the few projects I've seen attempt to use Druid is that there is quite a lot of infrastructure overhead / DevOps support required to manage a cluster at scale, and that fairly complex ingestion pipelines are required to load the data in the right format.

Anecdotally, I've heard that ClickHouse is easier to deploy from this perspective with similar performance, but would love to get others views / experience with these and similar data stores.

This review omits techniques from reinforcement learning (especially bandits) that have been used successfully in industry for years now.

Is this referring to the first version of the model, or DALL-E 2?

No, you are not your own relative.

> a thing having a relation to or connection with or necessary dependence on *another* thing

FWIW, there are many opportunities for significant ROI in ML / analytics projects.

Low-hanging fruit I've seen in this area has included automating or augmenting labor-intensive manual processes (e.g., classifying insurance claims), replacing human judgement with time-series forecasts within an ordering system, and optimizing email campaigns with RL.

There is also the possibility that the causation happens in reverse: those with early symptoms of dementia could be self-medicating with excess caffeine.

"Consumption of >6 cups/day was associated with 53% higher odds of dementia compared to consumption of 1–2 cups/day"