michaelbuckbee

I thought it was more implied, but let me be more explicit:

- This is something I made for myself without a lot of commercial thought, so I still haven't thought through pricing + usage + limits + operational limits. In it's current wildly unoptimized state it's still very cheap to run.

- For the specific concern about API Key leakage there's not a lot I can do about that (that I'm aware of) as the logic of what gets sent is handled by the client AI. It is possible to pull down and audit both the tools + instructions that are published by the MCP server if there are concerns on that side.

This is all very fair criticisms. This thread asked: "What are tools you have made for yourself?" and that's genuinely what this is. I wanted it so I made it and then AI makes it so easy to just throw up a marketing page.

I've a a handful of dev friends that have started to use it as well and give their feedback and it's been slowly growing as I've added sharing/invites.

I would absolutely not recommend putting big production data into it currently.

My vision for it was something more like how the #1 use of spreadsheets is actually people making lists and not actually people doing lots of calculations.

Given the uptake today (thanks everybody!) and your feedback (thanks Mystery-Machine) I'm going to work at addressing your concerns.

The funniest thing I've made is a free utility called "Moniker" that contextually renames files based on their contents.

Uses local AI models and I was able to snag this great domain name.

https://finalfinalreallyfinaluntitleddocumentv3.com/

But hands down the most useful thing I've made is HutchDB, which is a MCP service that you can call from any AI chat or Agent setup to store data for you.

Literally from your AI you just say "save that to Hutch" and then it figures out:

- The schema + fields - Builds nice webviews (Kanban, Timeline, Grid, Calendar) - Lets you share the output with people

So people use it for all kinds of things like time tracking ("every hour save a summary of my activities to Hutch"), for Agent to Human handoff ("Every day check social media for mentions of my company and save them to Hutch").

I use it for things like recording all of our marketing activities and then having my AI compare those to signups for rough attribution, etc.

Dead useful and at https://hutchdb.com

It's not just comparing all the models, it's also comparing all the providers and configurations of those models.

If you're doing any kind of production AI work you'll end up with outages caused by calling a single provider, OpenRouter seamlessly switching between providers is a godsend for uptime.

But even more than that there's meaningful cost+speed differences.

Here's Sonnet 4.6 being served direct, via Amazon and via Google

https://la9q13gg8w.evvl.io/

(spoiler: Google was both fastest and cheapest)

WRT the native grammar, consider adjective order. Few native english speakers (me included) can off the cuff name the proper order, but everyone knows the "right" order.

https://dictionary.cambridge.org/us/grammar/british-grammar/...

Assassin's Creed Brotherhood is kind of like that for the architecture and period it covers.

There's an interesting small YT channel that did a series on ACB + History

https://www.youtube.com/watch?v=hebq-fObdhY

That's a a lot less than I expected. Is it difficult to get coverage?

We're already seeing other states struggling with soaring house insurance rates (California and Florida) and a pattern of spikes in rates leading government mandated caps on rates leading to insurers pulling out of the states.

I've no idea what the going rate for insurance is currently in New Orleans but it has to be crazy right?

I was curious just how much of a difference there was, so ran a quick eval comparing them and fwiw DeepSeek is considerably slower but much much ~5x cheaper than Haiku and fwiw ~35x cheaper than Claude Opus 4.7.

https://07ytscmybx.evvl.io/

It it reminds me of a lot of friends who wanted to "start blogging" and their first step was writing a new static site system from scratch.

I was trying to get a better sense of the time cost quality matrix of these, so I threw together a quick eval of Sonnet 4.6, Mistral's dev model, and Opus 4.7 (figuring it's what you'd use if you were on Max).

The results for a function implementation and test of levenshtein distance in js are pretty similar but Mistral is 30x cheaper than Opus 4.7 and 4x faster than Sonnet 4.6.

https://5m6qnuhyde.evvl.io/

My plan was to just see if anyone wanted to actually use it first. That if I couldn't give it away I'd not invest the time in selling or open sourcing it.

I'd sort of designed it for my own needs first and hadn't thought too far beyond that.

I'd be curious to know if you consider a Lego store a "toy store". There's one that opened in my city fairly recently and is in an area of smaller boutique shops (kind of like what you described).

I made a B2C AI app that's fully local (and free) to do AI based contextual file renaming.

So if you give it a bunch of screenshots it will try and intelligently name them based upon what is in the screenshot. Same for videos, PDFs, etc.

But to your point I haven't even tried charging money as it feels like something Apple is just going to bake in as a feature.

https://finalfinalreallyfinaluntitleddocumentv3.com/

That's fair and fwiw something I'm in firm agreement with you, but also just not what I took from your comment.

Search ads do seem like the one ad type that kind of flips that though. Where it's not based on some general set of interests, but literally the thing you're searching for at that moment.

All of the cradle-to-grave studies I've seen about greenhouse gas emissions for renewables versus coal/oil still indicate massive improvements.

This government meta study of 3,000 such studies puts PV solar at roughly 20x less emissions than coal.

https://docs.nrel.gov/docs/fy21osti/80580.pdf

I took this a different way which was that to google railway is their customer and out of a variety of professional and security considerations want the communications to come from their customer and not them.

Something that the Overcast podcast player does (and probably others) is silence removal, which in some ways is even better than the raw speedup.

Exactly. The larger the organization the less percentage time devs actually are doing dev work and the less direct benefit there is from AI assisted coding tools.

Slightly different slice into this a very similar situation (local vs OpenRouter AI inference).

But in _every_ metric other than privacy it was better to run via OpenRouter than a local model, and not by a small amount.

Direct link to the comparison charts:

https://sendcheckit.com/blog/ai-powered-subject-line-alterna...

This sounds an awful lot like the early how to get on to the internet highway classes that existed. I don't think the classes had a lot of worth in the strict educational sense of like "here's how you do X Y & Z" but... We're I think much more effective at saying, you know, "X Y & Z are now possible."

It does take time and a little skill to know the edges of the AI tools. What's reasonable? What's not? What's likely to hallucinate? You could get something in the rough bounds of trust.

I can see a class helping with that.

The relevancy here is that he's denied the git history, versioning, branches, implicit documentation that even bad source control practices would have given him.

I have a friend that just picked up a new consulting job resurrecting an ancient Windows desktop application. No source control, no tests. And it's spread out over a dozen different folders with names like "_old", "_new" and "dates". Claude's doing a tremendous job in getting him to grips with what is actually happening in the application, what's relevant, what's not, what's different. I think it's literally saving him days and days at work.

Old person here. I think it's really hard to convey the extent to which smoke literally permeated everything. It's not just the immediate air quality aspects of it, but there was just a residue on all the surfaces, every cushion and fabric held onto the stuff.

I can recall the week that no-smoking indoors at restaurants/bars passed and it was literally shocking to walk into a place and not have it be hazy. It really felt weird.

Anyway, air quality + quality of life was much worse. Sometimes the future does get better.

To be clear, I tried to install it and it was a shitshow.

For years the family joke has been that when we take a family picture we need to take 5 because I will inevitably have my eyes closed in the first 4.

So I made an IOS app just for us that does face detection and won't take the actual photo until all of the detected faces have their eyes open.

I know a few people that are more or less prototyping little agents with it that monitor stuff for them and make some kind of discernment/decision about alerting them.

Nothing mission critical in any sense of it.

I ran a fairly large production test of this and on _every_ measure except for privacy it was worse than a free tier server hosted LLM.

Not happy about that as I would like to see more local models but that's the current state of things.

https://sendcheckit.com/blog/ai-powered-subject-line-alterna...

She's 50 years old has a doctorate in pharmacy and has worked as a hospital pharmacist for two decades.

I don't say this as a "gotcha", but more that even with all that experience she still finds it beneficial and helpful.