David Hobbs @jdavidhobbs

Making big website changes happen. || DC native. Hiker/cyclist. Peace Corps Chad. Photographer. davidhobbsconsulting.com Washington, DC Joined June 2008

Tweets

9K
Followers

2K
Following

1K
Likes

1K

David Hobbs @jdavidhobbs

11 hours ago

Often the very things that are lauded are those that ruin your digital experience. For instance, the accretion of microsites just makes it harder and harder for your visitors over time.

0 0 0 10 0

I've been searching for solutions to some use cases that newer LLMs finally help resolve. Here's some Use Cases for AI in Digital Presence and Content Analysis: hobbs.link/41HywVI Note: LLMs are not a universal cure and should only be used where it makes sense.

0 0 0 15 0

David Hobbs @jdavidhobbs

3 weeks ago

Would love to normalize prominently displaying what you're about to be charged, and not the "monthly" fee if you pay for a year. Show me the monthly price if I'm paying monthly, and the annual price if it's an annual subscription. Lead with that.

0 0 0 7 0

David Hobbs @jdavidhobbs

3 weeks ago

I miss breadcrumbs

0 0 0 8 0

David Hobbs @jdavidhobbs

3 weeks ago

I question time-on-page as a useful engagement metric. If someone can come to your site, find the info they need (or accomplish what they need), and leave quickly then isn't that ideal? Have there been any studies looking at whether time-on-page actually captures engagement?

0 0 0 22 0

David Hobbs @jdavidhobbs

3 weeks ago

The *class* of tool is probably more important than the particular tool.

0 0 0 10 0

David Hobbs @jdavidhobbs

3 weeks ago

A useful LLM use: walking through a website and just talking out loud about the problems/opportunities then having the LLM summarize. The bit I haven't worked out is how to automatically capture URLs of the pages I'm looking at.

0 0 0 17 0

David Hobbs @jdavidhobbs

3 weeks ago

When it comes to defining xpath/regex, I've found a useful feedback loop: 1. Give a stab at writing the pattern 2. Use the pattern to extract from some content 3. Ask an LLM why the pattern didn't work against that content Repeat.

0 0 0 8 0

David Hobbs @jdavidhobbs

4 weeks ago

You can ask an LLM to extract/summarize from content. At scale, this can work but it's slow and expensive. Or you can ask an LLM to define a pattern (for example xpath/regex) and then quickly and cheaply scrape it out.

0 0 0 18 0

David Hobbs @jdavidhobbs

4 weeks ago

In the end, you still need to define what you want to accomplish. And someone needs to be able to evaluate whether the approach (or code, or organizational processes, or tool, etc) has a chance of pulling that off.

0 0 0 18 0

David Hobbs @jdavidhobbs

4 weeks ago

One of the biggest things to define before sending out an RFP for web redesign/improvement: what is the extent of changes (which websites) and which backend systems will be impacted?

0 0 0 16 0

David Hobbs @jdavidhobbs

3 months ago

Sign up for the Beta: hobbs.link/2GKRMs8 Once invited: Enter URL → Chat with content inventory Content Inventories with AI

0 0 0 11 0

David Hobbs @jdavidhobbs

4 months ago

Hmm, I use em-dashes a lot— now I hear this can be a marker for ChatGPT output?

0 0 0 22 0

David Hobbs @jdavidhobbs

4 months ago

That moment when you're not sure how a bit of code ever worked.

0 0 0 20 0

David Hobbs @jdavidhobbs

4 months ago

Slack's AI search is often quite useful. This example query and response was quite helpful (based on conversations spanning over a year with a large gap in between).

0 0 0 24 0

Download Image

David Hobbs @jdavidhobbs

4 months ago

I asked Mistral's Le Chat if either Le Chat or Le Platforme (API) use inputs or outputs to train models. Le Chat responded unequivocally that it does not use inputs or outputs to train models. Their web page says same thing. But their current privacy policy says otherwise.

0 0 0 26 0

Download Image

David Hobbs @jdavidhobbs

4 months ago

We have got to come up with better responses than "good question". Maybe being more precise like "that question shows you deeply understand" or "that is an important but difficult question" or "I was hoping someone would ask that" or "that is a new question".

0 0 0 13 0

David Hobbs @jdavidhobbs

5 months ago

One thing missed in graph db posts you see on LinkedIn and elsewhere: rarely are graphs of useful data nearly as tidy as the pretty network diagrams show. In fact, in practice network diagrams are often not really useful except for exploration and troubleshooting.

0 0 0 23 0

David Hobbs @jdavidhobbs

5 months ago

Nice how Harvard is doubling down on the importance of research on its home page hobbs.link/4cG6ga9

0 0 0 17 0

David Hobbs @jdavidhobbs

5 months ago

I asked Google "What is Content Chimera". Couple observations: it heavily prioritized something I recently posted on LinkedIn about a feature I was working on (but not yet released), and it made a semantic mistake (equating my company with the tool), but overall not bad summary.