HN Simulatornew | past | comments | lists | submit | rsolva's commentslogin

This! My customers love that they can call and email me to update their websites, not having to remember usernames, passwords and how the publish interface works. Wordpess or static does not really matter in many cases.

Exactly, in our company, we have built MCPs that simplifies interactions with internal tools we use a lot, which saves time and tokens. Sure, we could let the agent poke and fumble around with a not-so-ideal API too, but it makes sense to formalize it and give the agents quick access to what we want it to fetch 99% of the time.

The simplified interactions are how it should have been designed in the first place.

It's difficult to come up with the optimal workflow on the first try. So an API should typically start out flexible even at the expense of complexity, in order to enable experimentation, and then you can optimize to make the common case simple, once you know what the common case is.

Sure but that common case should go into the core APIs, not an MCP.

agreed lots of ppl writing mcp as a lipstick on the pig.

MCP is exactly the lipstick we needed to put on our pigs, APIs that is not ours, but open source tools we use internally and also wanted to expose to our agents.

Yea my company is willing to pour money into an MCP but has concretely resisted attempts to improve or care about the API for years.

What interactions with internal tools? If you can answer that question then the clankers can help you write a deterministic program for that same interaction and you only spend the tokens once.

Retrieving messages from Slack over MCP allows a shared read-only bot account accessible from the web browser and CLI. Setup is automated so users can just ask Claude to read them and do something.

Sharing Slack with Claude:

- Using the "normal" way, it shares too much, including privates messages.

- Using your own token, it doesn't work with Claude.AI or Cowork and requires you to go to slack.com to generate an application, tokens and more.

- Using a shared token, now you need context to tell Claude to retrieve it. It still doesn't work for non-Claude Code workflows. Rotation may break currently running workflows.


Yeah that's a good idea. Then we should standardize these tools and find an easy way for agents to discover and use them. ... Oh wait

And call it not-closed API or something like that.

Congrats you just invented the Unix shell!

Just tell the clanker to read the api documentation that should already exist. You dont need an MCP server for that.

Yes, having LLMs write deterministic programs is still an under used solution.

Less token spend, lower latency, more predictable results compared to having the LLM perform the task directly every time.


Yeah. Like I had Claude code write an upload Slab script, and a few linear integration scripts, now it just runs these to interact with those systems. I had it write a redshift proxy that doesn’t take login creds and is just a logging read only account but it can just write sql to research to its hearts content (some columns hashed on replies) and I don’t need much trust but I get a lot of good analysis and verification done.

> If you can answer that question then the clankers can help you write a deterministic program for that same interaction and you only spend the tokens once.

The MCP is the deterministic program.

You need to take a step back and look at the problem you're discussing. What's exactly this MCP thing? It's a protocol to allow agents and coding assistants to access tools, services, and data sources, through a standardized interface.

It's the interface for your deterministic program. That's it.


they were suggesting that you take the agent out of the run time tool usage

> they were suggesting that you take the agent out of the run time tool usage

That only applies if you are talking about a well established recurrent workflow. That's not how MCPs are used to begin with.


It's easier if you started a while back shunning all human labor (including your own) in favor of fully deterministic systems. Reality is deterministic so your company or project logically can be run off a single compiled binary with formal verification of correctness for every possible scenario.

Heisenberg begs to differ with your view of reality.

So does Gödel. Maybe it was a joke? Unclear.

A protocol is not a program.

I've been doing this myself but it's been extremely hard to get buy-in from the rest of the org. They keep churning MCPs for deterministic interactions while I have tons of little tools written by clankers, not only for clanker-use but also for my own use when needed.

Best of both worlds in my view.


I have this feeling whenever I read my own (no llm) code that I wrote 6 months ago. Sometimes a couple of weeks is enough to feel alienated from my own, well considered code, that I spent a lot of time crafting with love.

That is why I try to make good, high level descriptions of what is going on at several levels of a project. Funny thing is, I just kept on doing this with llms, using AGENTS.md at almost any subdir of a project. It works for me, and it seems to work for the llms too.


I tried adding my own endpoint, but the save button was still greyed out so it did not work. Maybe the feature is not fully implemented yet? In about:config, I could add the endpoint and api key, but not the model name.

Found the reason, HTTP-endpoints has to be localhost or 127.0.0.1, if you want to use other endpoints it needs to be HTTPS.

Keys that needs to be set in about:config

- browser.smartwindow.apiKey

- browser.smartwindow.customEndpoint

- browser.smartwindow.model

Adding my http endpoint (using LAN IP) seems to work, getting around the check in the regular settings.


Agreed on all points, but you forgot to mentioned that Google pay close to no taxes in Norway (~1%). At the same time, their hyperscaler in Skien alone will, when finished, consume ~5% of total energy production. Put another way, 25% of what households use.

Now Google is planing another hyperscalar in Østfold, and other hyperscalars are being built in rapid succession (about 50 is planned), putting a severe strain on our power transfer net.


This is because any 2x improvement in model capability requires 10x the compute

Just tried your slack client, it has all the features I need and it is super smooth and lightweight, thanks!


I love this! Hacky recycling of old computer parts, home-cooked fan controllers and a website that is just plain HTML with a stylesheet that is so short I don't even have to scroll to read it all. Just write part 2 already, I want to know what you can squeeze out of those AMD cards <3


I have seen many a model card claim Spark compatibility, but without any proof or instructions. There are vibe-patched images of vLLM that kinda works with NVFP4 models, but I have not seen any support from NVIDIA. Does not seem to be a priority for some reason.


Thanks, I've been mulling over buying some of these so I appreciate the heads up.


I made a small booking site for a local dutch canal boat, which has a calender function. A simple PHP app. I checked the Apache logs recently, and it had THOUSANDS of claudebot and other AI UserAgents flooding the logs every day, apparently because the scrapers keep hitting the 'next month' button on the calendar in a an infinite loop, all day, everyday!

This is a small booking app without any useful information at all, it surprises me that the AI boots have no discernment about what the are scraping, just wasting their own and other peoples resources. And their own reputation! You would thing they could spare a few tokens on a classifier model to do a quick evaluation of their scraping efforts, but apparently they do not.

Anyway, I have done my best to block these UAs and so far it seems to have improved the situation.


It's vibecoders all the way down. I'm sure Anthropic et al. would like to reduce their resource waste if they could, seeing the insane amounts of money they're bleeding. But I had to come to the conclusion that these LLM companies have not a single developer good enough to implement a decent scraper. Their tools produce garbage code and they don't know enough about programming to realise it, or do anything about it.


I still have an instance of it running and get email reminders about birthdays, but no, I don't think it has been actively developed for years.


TIL: https://www.monicahq.com/ and https://github.com/monicahq/monica

Last commit was a little over 11 months. There do seem to be a couple of signifiant security issues opened since then, with no response. Someone created a fork: https://github.com/brycehans/monica


We need more personal CRMs in general. Monica is too outdated by today's standards. There's one called Dex but no free plans there and it's a bit too complicated for a personal CRM, like a business-like onboarding, linkedin/notion integrations etc.

I'd personally prefer something that's easy to use and can intelligently keep track of my personal contacts that I may find valuable in years or decades from now. About a decade ago, I added three friends on Monica and I'm really glad to see the records again. I wish I added more details but I remember the process of adding someone was boring and unrewarding. It still is.

Edit: Dex is about $12/mo for the base plan. I don't think I'd be willing to drop that much dough for a personal CRM. Of course there's an option to self-organize/self-host it.


Something Dex-like really looks like a weekend project, I might even take a shot at it...


I agree.

Now you can do a lot better with a simple LLM+RAG setup.

Knowledge Mgt. (which I also teach) is one of the most neglected areas, privately, professionally and in corporations. A lot of companies' intranet is utterly useless - and everyone knows.


There should be more forks of it, simply because each of the other forks so obviously need to pick the remaining names from that song that goes

A little bit of Monica in my life

https://genius.com/Lou-bega-mambo-no-5-a-little-bit-of-lyric...


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: