murmansk

Not the blitz author. Neo4j was freaking slow when I tried to use it.

Accelerando is a true masterpiece. Crypto and endless speculation, AI and lobsters, space exploration - all in all just "this is our near future". TBH, I know of just handful of Sci-Fi novels as fundamental and as let's say prophetic as this one. The others to my taste in the same category is Nexus trilogy by Ramez Naam (even if a bit farfetched by now), The Diamond Age (="The Illustrated Primer" is peak AI) by Neil Stephenson and Daemon+Freedom by Daniel Suarez (=AI + crypto DAOs).

Please, share! Especially, the trust part!

For gods sake, finally, somebody have said this!

I’ve been thinking a lot about how AI assistants evolve—whether they’ll keep absorbing specialized tools (like ChatGPT making search engines redundant) or if there’s another path. Model Context Protocol (MCP) feels like a turning point.

Most people talk about MCP as just a tool-calling API, but I think that misses the bigger picture. It could redefine how AI assistants work—not as standalone products but as dynamic platforms orchestrating external AI services.

In this article, I explore MCP’s implications through four angles: - AI Competitive Dynamics – Why generalist AI models tend to absorb specialized tools. - Economics of Complements – How AI assistants can thrive by enabling third-party tools instead of replacing them. - MCP as a Personal Agentic Platform – The shift from chatbots to deeply integrated AI assistants. - MCP as an Agent-to-Agent Protocol – Why AI systems should talk to each other instead of relying on humans as intermediaries.

I’d love to hear from others experimenting with MCP — does it feel like just another API, or is there something bigger here?

Or not a man, sorry for putting your identity into a bucket.

Man, this is just an awesome hack! Keep it up!

[flagged]

Sir, could you elaborate on how it is non-custodial, please?

Oh, and Discord invite is invalid.

So far, the most interesting part is "Link diagrams to let users drill down to details or browse related subjects". How do you do that? How does it actually look? The sign in process is prohibitively complicated, sorry.

Apart from this feature, looks like a glorified and confusing draw.io.

Oh, man, I was about to send this to my aunt, who is an actual architect. She designs houses. Was a bit confused discovering it is for IT diagramming.

While it might be great in theory, CBOR has own separate set of dragons waiting for you.

Expectation: tags in CBOR allow you to pass semantics. Reality: multitude of tags, and absence of strict rules for the tags make it pain in the ass.

Any documentation or code please?

Mind sharing why you consider this exciting, please?

Never! It gets just gets harder with time to find what you like, as your taste ossifies, and music evolves.

1% is where the problem is.

User side of false negatives: You miss skin cancer. The user delays a visit to a doctor by a month. The user dies in 3 months, and her relatives sue the hell out of the model creator.

User side of false positives: The model thinks a blemish is malignant. The user spends few grand to verify it is not, and blames you for scaring her.

Doctor side of false responses: The fucking engineers do not know what they are doing. Please, my patients, do not use that. We the doctors and the responsible patients should unite against the stupid AI.

Arguably, the user's side is about being moral. The doctor's side is more important for adoption.

BTW, what is the accuracy, false positives and false negatives for just an AI model, just a doctor, and a doctor equipped with an AI helper model?

Ahhaha, Intel's TDP is 2-4 times bigger under full load (and I guess ~10-15x under moderate load) while having negligible perf advantage over M2. The author can not be serious.

Based on the submission title I thought that was about Macromedia/Adobe product :D

When custom scripts in the perf testing workflow?

Some time ago I even created a list of non-financial blockchain applications: https://github.com/machinomy/awesome-non-financial-blockchai...

After few years I am convinced, that anything blockchain/decentralization related must inherently have some monetary incentives flow.

Anecdotic proofs: (1) I am a smoker, met with a bunch of later-diagnosed Covid people at a conference, did not get sick. (2) Spoken with doctors in my city, in Russia: there are virtually no smokers in Covid hospitals.

Yes, it is about 20 cents to open a channel, and 30 cents to close it.

This is a Node.js library that allows you to instantly* send a fraction of Ether as a payment for a HTTP service.

* - ok, if you have a payment channel open. A payment channel is an instance of state channels described on http://www.jeffcoleman.ca/state-channels/

It allows you to pay for just one SMS sent instead of having a minimal credit on Twilio, as an example.

Hi, HN, basically a one-man show here. Machinomy just turned v0.1, and I thought it could be a nice opportunity for feedback. Ultimate motivation for the project is to allow autonomous devices pay for themselves. This involves many things. The library is a prototype for the payments layer.

Some links:

[1] Project website: http://machinomy.com

[2] Code: https://github.com/machinomy/machinomy

[3] NPM: https://www.npmjs.com/package/machinomy

[4] Gitter Chat: https://gitter.im/machinomy/machinomy

[5] Twitter: https://twitter.com/machinomy