| ▲ | StrauXX 3 hours ago |
| I don't see much of a future for these kinds of intricate harnesses, or harnessing in general for that matter. As models are getting better, harnessing will shrink until they are at the level of vanilla Pi or not even that. |
|
| ▲ | Good4boothee 31 minutes ago | parent | next [-] |
| > As models are getting better, harnessing will shrink That can be true only for locally hosted models. The more supplied tools can do, the less data has to be exchanged with OpenAI/Anthropic servers. So bad harness means both higher lag and token usage. |
|
| ▲ | surgical_fire an hour ago | parent | prev | next [-] |
| Pi is a great harness because you can customize it with the building blocks that make sense for you. I think that harnesses for LLMs are as important as IDEs for languages. |
|
| ▲ | throwa356262 3 hours ago | parent | prev [-] |
| On the contrary, I belive this will be the next battlefield. My wild theory is that we already have AGI level models, but we are not yet using them correctly. |
| |
| ▲ | Octoth0rpe 3 hours ago | parent | next [-] | | My version of this theory is that we already have AGI, but Altman/Amodei/Zuck keep asking it for an infinite money glitch and it keeps (correctly!) saying "no money, humanity is fucked given the trajectory, and you in particular will be fucked once the general public decides that you're the scapegoat". A/A/Z decides the AGI is wrong of course, so obviously dumping another billion into training or reinforcement or tagging or whatever is the next step. | |
| ▲ | StrauXX 3 hours ago | parent | prev | next [-] | | If we had AGI, they could per definition build a harness better than any human could. In such a regime, (human) pre-built harnesses are moot. | | |
| ▲ | 010ED67913 2 hours ago | parent | next [-] | | agi is artificial general intelligence. sol5.6, astra, fable are already wildly more intelligent than the average person. we already have agi. however people need to keep the moving target so they have something to talk about, otherwise the voracious appetite for novelty will not be met. what we don’t have yet are the tools to take full advantage of the agi we do have. they’re coming soon. | |
| ▲ | throwa356262 3 hours ago | parent | prev | next [-] | | We maybe need an AGI level harness and an AGI level model to get there and we currently only have one of those? | |
| ▲ | ozozozd 2 hours ago | parent | prev [-] | | They said AGI is here. What you are describing is RSI. /s |
| |
| ▲ | grim_io 3 hours ago | parent | prev [-] | | Uhuh, sure. We are holding the AGI wrong. | | |
| ▲ | ozozozd 2 hours ago | parent [-] | | Always. Folks even believe all of us including themselves are holding it wrong. Kind of like how we all fail to see the bearded guy in the sky. | | |
| ▲ | puelocesar an hour ago | parent [-] | | Exactly, sometimes when reading Hacker News I get the impression this thing is a cult. Luckily there's still some dissident voice around to keep it interesting |
|
|
|
