I took a bit different approach assuming that agents can use the language servers to get structure and just trying to keep them honest. With this in a hook a lot of stuff is caught quickly without wasting a lot of context. https://github.com/dmoose/gochecks
Would you mind fleshing this out a bit? I'm not following how it identifies the sensitive pieces without sending to a model, or do you mean letting the model see messages, calendar, email, etc. but not able to go beyond those?
It’s similar to MCP, where in the Swift app I’ve got a catalog of actions eg, SearchEmail, AddToCalendar. I’ve got them bucketed by sensitivity so I have to approve (some of) them with TouchID.
So the model can see the results, but the access is whitelisted and temporary.
You aren't wrong, but that doesn't mean that ranking candidates and then choosing the one that is more aligned with your ideas isn't a valid strategy. This system is deeply broken but pointing that out and then putting a period on the end helps ensure it stays that way.
If he's trying to manipulate the economy in the direction of lowering cost of living, he's doing a terrible job at it. Useless wars and tariffs have been highly inflationary.
This presupposes that the llm will be able to pick up the slack for the users of imprecise language as to me that is a proxy for domain expertise. If so then the human is not needed which does seem like a stretch.
My view is that the human is needed for verifying the source of truth, not for providing precise language which the LLM is continuously trained to adapt better without.
I have not come across a rigorously argued technical analysis that has claimed that using precise language can in any way eliminate the possibility of hallucinations or unaligned behavior. Short of providing a proof for the elimination of hallucinations and confabulations, merely reducing the behavior by a random percentage is not an acceptable status quo for completely removing the human.
I think the argument that precise language doesn't matter is even harder than that.
It requires that LLMs are equally effective with imprecise language as precise language.
And while I'm sure the frontier labs are continually iterating on 'garbage in, something vaguely useful out', it's a high bar to get that output to be as useful as if it were more precisely prompted.
For those of us without a degree in economics the last few years have seemed a bit unhinged from reality so I will not claim any deep insight here. However, it is hard to imagine that an increase in cost of debt will not have some impact and probably in ways not anticipated by many of those with economics degrees.
This! $1.6+ TRILLION in infra spending from the big frontier labs. The earnings needed to drive a reasonable ROI to recoup that investment is simply not going to happen in a time frame where the numbers make sense.
The other insanity in all this the smartest computer scientists in the world are asking Congress to regulate them. Come. On. Really? Do we remember “The internet is not a truck, it’s a series of tubes…”
Why can’t the big labs form a Save The World Consortium and self-regulate?
Non-democratic counties (hey there China) will not abide by any agreement that constrains their advantage. It’s naive to think so.
What this conversation lacks is enough discussion of how these models can cause us harm—we are are so worried about AI but we allow Windows in critical infrastructure; we build JS/TS apps with thousands of dependencies; we generally don’t segment networks well enough; we don’t have adequate (sometimes any) detection capabilities in our systems, and so on.
In a prisoner's dilemma the players can't rely on one another to self-regulate. This is why Mafias kill snitches, so when their members are in a prisoner's dilemma they can rely on the knowledge that if themselves or the other party snitches they have more to lose than gain.
The problem is that there can not be any outside party to regulate this on a global scale
There's plenty of precedent for specific industries self-regulating in the US, typically motivated by the shared view that it would be less disruptive than heavy handed federal regulation.
Applying game theory problems like prisoner's dilemma to the real world requires collapsing a lot of overlapping and conflicting incentives to a single dimension which doesn't always work.
In this case the goal is bringing about the singularity, basically creating a sort of godlike intelligence. That's what the arms race is all about.
So we are in a true prisoner's dilemma, if one of the companies / countries stops R&D it risks handing over godlike power to another company / country.
> Non-democratic counties (hey there China) will not abide by any agreement that constrains their advantage.
The main counterexample to this was nuclear weapons. Atom bombs have not been used to kill since the US did so. However today, the two largest nuclear powers have no legal agreement on arms control because Donald the Trump declined Russia's offer for an extension to the existing agreement. Now other countries are looking at Ukraine, Iran (attacked for wanting nukes) vs NKorea (not attacked because they have them), and Donald's own musings about the US nuclear umbrella being a bad idea (France is going to build more nukes now too)... and we now face nuclear proliferation again on a global scale, with tech that is nearly 100 years old now.
This isn't about individuals. The Republican Party is completely complicit and as long as members of that party hold office they will continue. I would love to have multiple qualified candidates to choose from across the spectrum but right now the system has been co-opted and a hard reset is the appropriate response.
reply