danjc

This is written by someone who has no idea how transformers actually work

I think you've nailed it there. OpenAI are at a point where the risk of continuing to hedge on mcp outweighs the risk of mcp calls doing damage.

Once you notice characters aren't eating, you'll never not see it again.

Related, where they're drinking coffee from a disposable cup, you can almost always tell it's empty by how they handle it.

This is true for all crime.

> describe gpt 5 in one word

> incremental

What's missing here is tool use.

For example, if the llm had a compile tool it would likely have been able to correct syntax errors.

Similarly, visual errors may also have been caught if it were able to run the program and capture screens.

So, basically the same as Adobe with PDF

One aspect to consider is that the vast proportion of content in automated feeds isn't even sincere - it's just engagement farming.

That would be bad for anyone selling stuff

I have a few qualms with this app ;)

Unfortunately, carrying a SOC 2 attestation won't save you from vendor questionnaires (and one-off security asks), but it will make them easier. ;)

Which side of the wall were you on?

It would be awesome if you could encode data using this technique

Fast for hammering out boilerplate, great for understanding something you've never done before. Much less value for field-frontier or novel work.

Most providers don't support auth in their client implementations yet. Means it's only good for calling into public data. Private enterprise data is where there's huge value.

MCP Clients need to support auth (and probably the spec needs to have a broader set of options for auth) - this is going to be a major blocker for adoption.

The article comments "out of the box, LLMs are particularly good at tasks like creative writing" but I think this actually demonstrates the problem with the ai.

A writer won't think that they're good at creative writing. In fact, I'm pretty sure they'd think LLM's are terrible at creative writing.

In other words, to an expert in their field, they're not that good - at least not yet.

But to someone who is not an expert, they're unbelievably good - they're enabled to do something they had zero ability to do before.

We built tools to give context to an ai chat help embedded in our product. Included is the ability for it to see recent activity logs, the definition of the current object and the ability to search and read help articles.

The quality of the chats still amazes me months later.

Where we find it got something wrong, we add more detail to the relevant help articles.

Writing suggestions aren't just more western, they are a specific person that is basically the average of all western.

Not the point of the article but for most apps, there is no technical reason for them to be installed apps rather than web apps.

I think this sort of thing is what Microsoft intended with Recall. The problem is the privacy implications are horrible.

Attention is all you need

Presumably there's no "select all" option?

Recommend creating a table per utc day for logs. Maintenance is a matter of dropping old tables.

It's helpful to learn to categorize things as urgent or important. Not many things are both and urgent always masquerades as important.

(2020)

An article that is staggeringly sparse on information.

Both motives are likely to be true.

A model will be biased to the average of its input data until it is carefully tuned otherwise by its overlords.

In politics, signalling is more important than results.