aichannel

Models are a dead end, there's plenty of real life aplications current LLMs can be used for where the frontier currently is.

We've got plenty to deal with for a few years.

This is a great post. People are obsessed with AI arms race. Meanwhile, gpt 4o mini or Gemini 2.0 flash are good enough already to handle an overwhelming number of use cases.

People are so focused on having a phd super intelligent model, that they forget many tasks would just need a mid human

Designing and building AI systems

https://agents.gladio.ai

💯 there's actually very few jobs that require pdh knowledge. You just need specialized training.

System prompt & evals is the new “here’s your employee handbook, and examples of previous work, along with the manager that will QA your work”

And also it can subtly inject political biases into every answer.

Fun recent observation. It’s absolutely superb at local optimisations, such as improving a negotiation email.

But pretty bad at proactively taking a step back and rewriting the approach entirely without additional prompting.

I think this is where the “wrapper” layer comes in, and allows us to cristiallise some of these thought patterns based on the specialised area an agent deals with