I usually skim/scan before reading anything. I used to do this to get a gist of what to expect, but now I do it to look for telltale signs of AI slop (and run through Pangram if I’m suspicious) before committing to reading

Claude tried to massively increase the scope of this essay after reviewing my first draft. In the editing process it also added a bunch of emdashes to my writing. It's very hard to resist.

You should try writing about what we lose when we use AI to write blog posts.

This has more to do with Voice Activity Detection (VAD) than the latency described in the article

That seems to be the issue: VAD is insufficient here.

Knowing when to respond requires semantic understanding, which probably only the model itself is capable enough.

Maybe it’s hard for them to train it to only respond once it seems appropriate to do so?

I am excited for VAD to go away. PersonaPlex totally seems like the future.

However things like 'Call center helpline' turn based actually seems better! You don't want to be interrupted when giving information back and forth (I think?)

Exactly. It's a tangent, but clearly a pain point for enough users.

Thanks for WebRTC for the Curious and for Pion! Not using the latter directly, but have used both to better understand WebRTC

This is one of the coolest hacks I've seen recently. Having done some much less involved MacOS hacking, I can't help but wonder if we may finally see momentum behind some flavor of agent-friendly Linux/Android if Apple doesn't give us more ways to let agents interact with our machines.

really appreciate it. macOS has powerful primitives already, but they weren’t designed as one coherent agent API so you end up stitching together and hitting roadblocks. If Apple doesn't make this more first-class, Linux/Android-style environments may move faster because they’re easier to instrument. I think the OpenAI/Jony Ive AI hardware rumors are yet another signal that people may start building agent-native CUA devices instead of retrofitting agents onto existing desktops

Potentially, but likely much less effective and less studied, and you likely need longer sessions for effective dosage.

Most of the studies I've seen on improvements in blood plasma volume from passive heat are usually done with sessions in saunas with temperatures > 150 degrees F (60 C). Steam rooms usually only get up to 120F (~49C) even though the humidity probably makes it feel warmer.

Copying and pasting some of my reply to another comment above

Sweating is one the main triggers for an increase in blood plasma volume, and the humidity level of a steam room causes vastly higher rates of sweating than most saunas do. You can lose significant body heat by sweating in a dry environment, but much less in high humidity. Consequently, your body needs to sweat much more rapidly even though the absolute temperature may be lower.

To my understanding, while sweating is important to heat adaptation and blood plasma volume adaptations, thermal load and cardiovascular strain are likely bigger factors (and more important for the health benefits mentioned in this study). Overall thermal load is still higher in a hotter dry sauna than in a steam room

That's not my understanding, but my understanding is somehwere between 3rd and 6th hand, so it's likely not worth much.

FWIW, most of the studies on improvements in blood plasma volume from passive heat are usually done on saunas with temperatures > 150 degrees F (60 C). Steam rooms usually only get up to 120F (~49C) even though the humidity probably makes it feel warmer.

Thanks for trying it, and keen eye! Fixing (with Claude code) but also taking time to try to learn a bit about the canvas drawing/pixel art, which I'm not super familiar with.

Sure! If you’re just drawing things directly polygons, lines, and other primitive shapes, then you can usually get away with just turning off anti-aliasing, and that will fix most visual artifacts and get you closer to that classic Apple II Oregon Trail look.

However, if you’re using pre-rendered sprite sheets, you’ll probably need to enforce integer scaling to avoid fringing or blurring.

Ah yea, I got an uncommon dragon instead of the rare duck. Did you get your legendary?

Nope :| Still a ghost, but it's just common now, too bad

This is awesome! Working on a desktop pet so the buddy caught my attention. Looking forward to making friends with my Rare Duck buddy tomorrow. Wish it was a snarky duck instead of a patient one though.

Do you think LLMs make this process of starting the engine easier or harder? They make getting started much easier, but it might be harder to feel a sense of momentum since our expectations of speed have changed, and the learning moments have changed as well.

The bug is in the software in our heads, if anything. We learned a little too much, that we're thinking further ahead than we would have when we first started out. So you need to purposefully shut off that part of your eval, so that you get started on anything at all.

If you design with the LLM, then it can make this easier by prompting it to help you not talk yourself out of things.

I found that gstack's /office_hours to be good about encouraging, while being firm. I've only done one of the modes, but it didn't dismiss my pushback when it was just based on my intuition. It took it as a baseline, and tried to evaluate it by taking it seriously. If that's any indication, the other modes for side projects should be just as supportive.

I think LLMs can make it easier to be more ambitious. Non-techies are blown away by being able to build web pages? I'm blown away that I was able to root my 1st gen Kindle Fire to repurpose it as a remote terminal to ssh into my laptop to talk to claude code. I've been trying to root the thing for years and could never find the right instructions to make it work.