I use MCP for a voice assistant as well.

I got a Pebble Index 01 ring and it has support for custom MCP servers. I run one on Tailscale and it can interact with Home Assistant, my home issue tracker, my Anki setup, etc.

I've come full circle on MCP. With agents with a shell tool they quickly became unnecessary but these days I've been coming up with more agentic use cases where I don't want to give the agent a shell, and a narrower MCP interface is a great fit.

You just convinced me to buy a Pebble Index, which I was on the fence about. No idea it supported MCP servers.

Ah, thanks. It's been hard to plan around these last-minute changes. I rushed to implementation on a spec I should have spent more time on because of the looming deadline.

I use both now and agree they're basically interchangeable.

I appreciate that Codex is open source and OpenAI has explicitly said using the subscription with other agents is ok. OpenAI has been much more consumer-friendly recently.

And OpenAI didn't try to silently degrade performance of their top model if its (extremely sensitive) safety sensors went off ...

Anthropic is the silver lining keeping p(doom) below 1.0

I like Codex for allowing auto_review.policy (basically a prompt to the classifier on what to allow/disallow) to be configured rather than the opaque auto mode in Claude.

For me as well, at least this month to use more of Fable. We'll see if they extend Fable access because of people like me.

I'm pretty sure the system instructions are a function of your environment and not the same universally. That said, there should be a finite number of branches so still cacheable.

System specific stuff is probably quite limited, it can be a short dynamic segment at the end of the system prompt, perhaps.

I'm amazed at how steep the AI learning curve continues to be and how people are spread so far apart on it. I think supercharged learning with AI and agents is undervalued at this point but that more people will realize its utility over time, especially as a complement to delegating work.

It also makes me think about the temptation to stop thinking with these tools, i.e. "cognitive surrender". Addy Osmani wrote a nice blog post about this: https://addyosmani.com/blog/cognitive-surrender

Agents completing work faster would certainly help me as well since I also find context switching exhausting above some threshold.

Build and test would move back into the critical path, though, and for some projects that will take effort to bring down.

Direct link so others don't have to look them up: https://www.facebook.com/photo.php?fbid=10151143106612055&se...

It's actually 0.05% more for a $20 item, and if we estimate that $20 is the average price of all items it isn't very significant.

I was able to get a couple of specials honored in SF (buy one get one drinks in both cases).

Recently I've seem some of the specials requiring an AMEX credit card linked to my foursquare account, which I feel crosses the "worth it" line.