[HN Gopher] Anthropic AI
___________________________________________________________________
Anthropic AI
Author : vulkd
Score : 75 points
Date : 2021-05-28 17:25 UTC (5 hours ago)
(HTM) web link (www.anthropic.com)
(TXT) w3m dump (www.anthropic.com)
| gavanwilhite wrote:
| This looks quite promising!
| mark_l_watson wrote:
| I agree! Love the public benefit aspect of Anthropic.
| Animats wrote:
| Their paper "Concrete problems in AI safety"[1] is interesting.
| Could be more concrete. They're run into the "common sense"
| problem, which I sometimes define, for robots, as "getting
| through the next 30 seconds without screwing up". They're trying
| to address it by playing with the weighting in goal functions for
| machine learning.
|
| They write "Yet intuitively it seems like it should often be
| possible to predict which actions are dangerous and explore in a
| way that avoids them, even when we don't have that much
| information about the environment." For humans, yes. None of the
| tweaks on machine learning they suggest do that, though. If your
| constraints are in the objective function, the objective function
| needs to contain the model of "don't do that". Which means you've
| just moved the common sense problem to the objective function.
|
| Important problem to work on, even though nobody has made much
| progress on it in decades.
|
| [1] https://arxiv.org/pdf/1606.06565.pdf
| ansk wrote:
| I can't find any mention of who currently comprises the core
| research team. It mentions Dario Amodei as CEO, and their listed
| prior work suggests some others from OpenAI may be tagging along.
| However, the success of this group is going to be highly
| dependent on the caliber of the research team, and I was hoping
| to see at least a few prominent researchers listed. I believe
| OpenAI launched with four or five notable researchers as well as
| close ties to academia via the AI group at Berkeley. Does anyone
| have further info on the research team?
| chetan_v wrote:
| Seems you can see some of them on their company linkedin page :
| https://www.linkedin.com/company/anthropicresearch/about/
| ansk wrote:
| LinkedIn authwall, we meet again. Could someone list the
| researchers (if there are any, and assuming there are only a
| few). Frankly, it's not a great sign that the Anthropic site
| isn't touting the research team itself and LinkedIn sleuthing
| is even necessary.
| Qworg wrote:
| Current list (in LI order):
|
| * Dario Amodei
|
| * Benjamin Mann
|
| * Kamal Ndousse
|
| * Daniela Amodei
|
| * Sam McCandlish
|
| * Tom Henighan
|
| * Catherine Olsson
|
| * Nicholas Joseph
|
| * Andrew Jones
| ansk wrote:
| Thank you.
| phreeza wrote:
| Chris Olah posted that he is involved.
| n1g3Jude wrote:
| Complete waste of money.... Better to burn cash directly cause
| that at least generates heat... This will generate nothing
| etaioinshrdlu wrote:
| Since this is Hacker News, I'll point out that training on GPUs
| produces plenty of heat.
| m4t3june wrote:
| That's not true, they might generate some heat with the GPU
| training
| joe_the_user wrote:
| Looks like an interesting project. The thing is, I don't think
| ideal qualities like "reliable, interpretable, and steerable" can
| really be simply added "on top of" existing deep learning systems
| and methods.
|
| Much is made of GPT-3's ability to sometimes do logic or even
| arithmetic. But that ability is unreliable and even more spread
| through the whole giant model. Extracting a particular piece of
| specifically logical reasoning from the model is hard problem.
| You can do it - N-times the cost of the model. And in general,
| you can add extras to the basic functionality of deep neural nets
| (few-shot, generational, etc) but with a cost of, again, N-times
| the base (plus decreased reliability). But the "full" qualities
| mentioned initially would many-many extras-equivalent to one-shot
| and need to have them happen on the fly. (And one-shot is fairly
| easy seeming. Take a system that recognizes images by label
| ("red", "vehicle", etc). Show it thing X - it uses the categories
| thing X activates to decide whether other things are similar to
| thing X. Simple but there's still lots of tuning to do here).
|
| Just to emphasize, I think they'll need something extra in the
| basic approach.
| Der_Einzige wrote:
| Go check out the entire project of captum for pytorch. I assure
| you that gradient based explanations can be simply added to
| existing deep learning systems...
| joe_the_user wrote:
| All sorts of explanation scheme can and have be added to
| existing processes. They just tend to fail to be what an
| ordinary human would take as an explanation.
|
| Note - I never argued that "extras" (including formal
| "explanations") can't be added to deep learning system. My
| point is you absolutely can add some steps at generally high
| cost. The argument is those sequence of small steps won't get
| you to the ideal of broad flexibility that the OP landing
| page outlines.
| chetan_v wrote:
| Looking at the team seems to be all ex-openai employees and one
| of the cofounders worked on building gpt3. Will be exciting to
| see what they are working on and if it will be similar work to
| openai but more commercialized.
| andreyk wrote:
| Excited for this! While OpenAI has generated plenty of overhyped
| results (imo as an AI researcher), their focus on large scale
| empirical research is pretty different from most of the field and
| had yielded some great discoveries. And with this being started
| by many of the safety and policy people from OpenAI, I am pretty
| optimistic for it.
| strin wrote:
| https://techcrunch.com/2021/05/28/anthropic-is-the-new-ai-re...
___________________________________________________________________
(page generated 2021-05-28 23:00 UTC)