foota

I don't know how far it would get, but I imagine that a FAANG will be able to get the farthest here by virtue of having mountains of corporate data that they have complete ownership over.

I think the more interesting question here would be if someone could fine tune an open weight model to remove knowledge of a particular library (not sure how you'd do that, but maybe possible?) and then try to get it to produce a clean room implementation.

Ah yes, open API, famously a user accessible means of accessing a website.

Well that aged poorly.

Hm.. but that's just tool calling, right? MCP is just that there's a lot more tools than normal.

Does tool calling in general bloat context, or is there something particular about MCP?

One thing I have read recently is that when you make a tool call it forces the model to go back to the agent. The effect of this is that the agent then has to make another request with all of the prompt (include past messages), these will be "cached" tokens, but they're still expensive. So if you can amortize the tool calls by having the model either do many at once or chaining them with something like bash you'll be better off.

I suspect this might be why cursor likes writing bash scripts so much, simple shell commands are going to be very token heavy because of the frequency of interrupts.

That's... weird? Maybe it's blocked in your country? The link opens just fine for me.

Those were tested numbers, not advertised though. I don't see how you'd get a drop from 200 to 120 miles, that's a 40% drop. Maybe in a gasoline powered car, but EVs can regeneratively break, so I don't think it'd make that much of a difference.

Reading some more, there are a handful of different ratings. the old European one: NEDC, the new European one: WLTP, the US EPA, and China's CLTC.

Generally the ratings from lowest to highest go EPA, WLTP, NEDC, then CLTC. The EPA rating is just a tad high I've read when you look at fast highway driving (e.g., 75 MPH), but should be within ballpark range.

I think you're under estimating the range of modern EVs.

Maybe most EVs in the wild, but no way for EVs being sold today. There are only 5 cars on this list below 200: https://www.edmunds.com/car-news/electric-car-range-and-cons..., and more than half above 300.

> This makes it a little more expensive than diesel, considerably more expensive than petrol, and roughly the same price as electric

Is electric charging more expensive in the UK than petrol? That's nuts.

> Hydrogen is such a terrible idea it was never getting off the ground.

See: the Hindenburg disaster

afternote: There's the potential for an amazing pun in here, but I don't think I quite did the opportunity justice.

That makes sense! The only flaw here imo is that sometimes that thinking is useful. Sub-agents for tool calls imo make a nice sort of middle ground where they can both be flexible and save context. Maybe we need some tool call composing feature, a la io_uring :)

What do the calls being sequential have to do with tokens? Do you just mean that the LLM has to think everytime they get a response (as opposed to being able to compose them)?

No, I don't think you're thinking about this right. It's more like hacker news would expose an MCP when you visit it that would present an alternative and parallel interface to the page, not "click button" tools.

I've been having much the same thoughts. What will work look like, say, 10 years from now? I'm beginning to think that we might have all the knowledge worker type jobs largely filled, or filled with significantly less workers, (hopefully) more free time for everyone, and the remaining people working in more physical positions.

In many ways, I think this is probably better for society than the opposite, since in general there are fewer knowledge workers than not.

My understanding is it's liability, if the doctor decides not to look into it then they could be blamed for it if it turns to cancer.

Wow, I wouldn't have thought that it would be possible to do this (at least, not ergonomically, although now that you mention it I guess I don't see why not). That would be amazing to see.

I was sort of thinking about a similar idea recently. What if you wrote something like a webserver that was given "goals" for a backend, and then told agents what the application was supposed to be and told it to use the backend for meeting them and then generate feedback based on their experience.

Then have an agent collate the feedback, combined with telemetry from the server, and iterate on the code to fix it up.

In theory you could have the backend write itself and design new features based on what agents try to do with it.

I sort of got the idea from a comparison with JITs, you could have stubbed out methods in the server that would do nothing until the "JIT" agent writes the code.

No? It sounds like they rejected the need for a connection pooler and took an alternative approach. I imagine they were aware of connection poolers and just didn't add one until they had to.

Imho (in my harsh opinion, in this case) unless you're a prodigy you're probably not a very good programmer at this point. Now granted people learn more quickly outside of university I think because it tends to be more focused, but I don't think I know anyone that I would have called a good programmer a year in.

But feel free to call yourself a programmer, I'm not going to gatekeep it :)

Yeah, this is for integration with OTEL standard distributed tracing. So you configure some OTEL compliant endpoint for postgres to send trace spans to and that endpoint will collect traces from different services and store them for later retrieval.

Distributed tracing is a term for tracing that span between systems. With distributed tracing you can follow request traces across your various services. With pg_tracing enabled in postgres this would extend to your database.

My guess would be cache related. 5k probably fits in L1-L2 cache, whereas 20k might put you into L3.

There's been trials of sails for cargo ships.

The FCC and the FAA are two federal agencies that really don't want to mess with, so I hope for their sake they didn't actually spoof it. (.... I wish there were an FBB as well)

Wow, someone in the github comments[1] noticed that one of the bug numbers assigned internally for the issue matches to the day the number of days the driver would stay up.

1: https://github.com/NVIDIA/open-gpu-kernel-modules/issues/971...

shrug YMMV. I was definitely a bit of of a luddite for a while, and I still definitely don't consider myself an "AI person", but I've found them useful. I can have them do legitimately useful things, with varying degrees of supervision.

I wouldn't ask Cursor to go off and write software from scratch that I need to take ownership of, but I'm reasonably comfortable at this point having it make small changes under direction and with guidance.

The project I mentioned above was adding otel tracing to something, and it wrote a tracae viewing UI that has all the features I need and works well, without me having to spend hours getting it up set up.

Imo programming is fairly different between vibes based not looking at it at all and using AI to complete tasks. I still feel engaged when I'm more actively "working with" the AI as opposed to a more hands off "do X for me".

I don't know that the same makes as much sense to evaluate in an essay context, because it's not really the same. I guess the equivalent would be having an existing essay (maybe written by yourself, maybe not) and using AI to make small edits to it like "instead of arguing X, argue Y then X" or something.

Interestingly I find myself doing a mix of both "vibing" and more careful work, like the other day I used it to update some code that I cared about and wanted to understand better that I was more engaged in, but also simultaneously to make a dashboard that I used to look at the output from the code that I didn't care about at all so long as it worked.

I suspect that the vibe coding would be more like drafting an essay from the mental engagement POV.

I watched Night Crossing in my german class in high school. I remember it being intense.

Slightly off topic, but they want to move from solid to react? Isn't that the reverse of the newest trend? Would be interesting to know more.

I've always liked the idea of intelligence in the autonomous ships of the Revelation Space universe. Little agents reporting to progressively more intelligent and higher level ones.