andreidbr

"Humans have a token limit too" - that's so good and it explains so much of the fatigue that myself and colleagues/peers have about Claude in particular.

I've been using the Chrome CDP skill for Claude Code with great success for test automation purposes (locator detection, troubleshooting mobile layout, and so on). I found it here on HN: https://github.com/pasky/chrome-cdp-skill

I remember seeing another Chromium-based "MCP-focused" browser at that point in time, but I can't remember what it was called.

Same for me. I also download videos and put them on a USB stick plugged into the TV.

I recently migrated to a new phone and one of the apps I had to re-login was Dropbox. A feeling of nostalgia washed over me. It was absolutely essential many years ago but now the competition is huge. I'm not a fan of Private Equity but if it can keep the business alive, then it's worth exploring by the leadership.

I've worked on a LLM-based visual validation framework for mobile layouts of different websites. The results are pretty flaky, even with Claude models. I've actually seen better performance with older ones like Meta Llama 4 or Amazon's Nova (the solution was running on AWS Bedrock).

I've since refactored it to first do some deterministic checks using CSS, to determine visual glitches like overlaps. Only after do I use LLMs to figure out if text is broken, loading spinners still display, or other such things where models are better.

For deterministic tasks like pixel-by-pixel comparison, I don't think LLMs are good enough (for now, at least).

I am a Hover user for my personal website, on a .com domain. I've been extremely way of using any of the customized TLDs since I heard about these sort of massive hikes. I agree that the communication could have been much better on Hover side, especially with such a huge increase.

Really nice presentation and a ton of useful info. It's hard to boil it down to a single reading though. One thing that would be nice is a bit of a comparison between what companies claimed to do vs what they're actually doing, like a sort of BS meter.

I also agree.

"Making kids" is fun, duh.

Raising kids, however, can be very challenging in all sorts of ways. Physically, mentally, socially, etc. I became aware of just how much sleep deprivation affected me and for the sake of myself & my family I just sacrificed everything else to ensure I got good quality sleep. Fortunately, I was helped in this and I made damn sure everyone was supported when I was awake.

This also annoyed me a lot. I was running it before upgrading the SSD storage and I wanted to compare with LM Studio. Figured it would be good to have both interfaces use the same models downloaded from HF.

Had to go down the same rabbit hole of finding where things are, how they're sorted/separated/etc. It was unnecessarily painful

I enjoy Tim's content and in the last couple of years he's definitely gone beyond his established "shtick". He's definitely done his own "dog-fooding", testing advice on himself and he's found some awesome people along the way.

I'm happy that he has gone beyond the "book / author of the week" format and this blog post is most welcomed.

Relationships are crucial, especially ones that help elevate yourself or, at least, keep you on a stable level instead of dragging you down.

I wholeheartedly agree with point 7 Your goal is for your team to thrive without you.

I spent a lot of time also playing a Scrum Master role in addition to my regular duties. So much so that some managers asked me to pursue this full time. I always explained that my goal is to be there just as a point of contact and that the team should be able to manage itself.

Sadly, I see so many managers, scrum masters, or even regular engineers consider this as a dumb approach to make yourself replaceable. If you don't hoard knowledge then you'll be laid off when the company's numbers look bad.

Same. I was looking to see if others had the same experience. With a toddler and my personal goal of being as present as possible with him, I rarely find enough time to use it. When he sleeps, I go on the PC and that's it.

Maybe as he gets older. Until then, I'm just periodically charging it up.

I re-read most of the stories a few years ago. It's shocking/surprising/depressing just how many things repeat themselves. From the obvious, veteran of Afghanistan war in the form of Dr. Watson, to London being a melting pot of so many cultures, with high society reigning from ... on high.

I also agree that the view directly into the state of mind of both Watson and Holmes was refreshing.

I see this sort of thing, plus additional broad-spectrum check-ups recommended in a lot of podcasts, particularly those geared towards being more efficient/productive.

On the one hand, good for those that can afford it, but I do hope they're not uselessly occupying the machine & labs, thereby making it hard to people who need them for relevant medical reasons.

Honestly, because the barrier to getting an MVP is almost non-existent, you see a lot more people trying to actually implement their ideas, instead of just relinquishing them to a list of ideas never to see the light of day.