Comments URL: https://news.ycombinator.com/item?id=49864802

Points: 1

# Comments: 0

The early batch of Anthropic employees were mostly rationalist-adjacent AI safety folk that were almost uniformly claiming P_DOOM > .10 three years ago, so I believe them to be earnest.

It's very interesting to me that besides the other small safety labs that don't actually produce frontier models, Anthropic manages to keep such a good reputation within that subculture compared to OpenAI. Despite having as crazy internal politics as OpenAI, they have converged quite a bit from the original vision of safety first through Darwinistic pressures.

At least, it seems this way from the outside. I'm curious if the view from the inside is that different.

edit: to be clear, my reading as an outsider is that Anthropic is seen as relatively better in the AI safety community, but has definitely dropped in absolute reputation too. This recent thread and the references show some of that: https://www.lesswrong.com/posts/6j3kBHdowGLCeqobg/dear-god-p...

From this they get rapid growth, namely > 100% GDP growth around 2031

https://ai-2040.com/supplements/econ-explorer

It's very interesting to me that besides the other small safety labs that don't actually produce frontier models, Anthropic manages to keep such a good reputation within that subculture compared to OpenAI. Despite having as crazy internal politics as OpenAI, they have converged quite a bit from the original vision of safety first through Darwinistic pressures.

At least, it seems this way from the outside. I'm curious if the view from the inside is that different.

edit: to be clear, my reading as an outsider is that Anthropic is seen as relatively better in the AI safety community, but has definitely dropped in absolute reputation too. This recent thread and the references show some of that: https://www.lesswrong.com/posts/6j3kBHdowGLCeqobg/dear-god-p...

https://dylancastillo.co/posts/pelicanmaxxing.html

https://news.ycombinator.com/item?id=49010129

The party is a is a relatively small concern compared to the openness and github comparisons, but since no one else mentioned it, I hope something like it happens again. Or maybe that moment has passed.

Hopefully it's just another A/B they drop after a week like in the past, but otherwise I may have to move on to another semi-anonymous doomscroller.

Comments URL: https://news.ycombinator.com/item?id=49360802

Points: 2

# Comments: 0

It's hard to keep track of the frontier on bio ML, but it seems that we're going slower than what Demis Hassabis said in 2024 with 5 years to full cell molecular simulation. We still aren't able to reliably model a tiny surface of the cell membrane.

And of course there's Derek Lowe's takes on the drug discovery pipeline waiting for the proof in the pudding.

To me the only reasonable bullish position is that there is a very non-linear AGI threshold for accelerating progress that we haven't hit yet.

For me personally, I'm looking at other more tractable fields as a proxy to measure this kind of progress. The best modest evidence is from the agentic coding area, (modest because these kinds of gains may not translate to bio progress). Other soft-ish fields to like legal/law/tax are also interesting to watch, as a small amount of people are now trusting AI for these areas that were considered totally unusable a year ago. Another proxy is being able to generate generally entertaining media.

LADW and LADR are great too, for an honors approach with more focus on proofs. To me it would make more sense on a second pass.

For an SRE there can be more directed hate received from the junior employees, that want to release new features they developed. Especially because there is less accountability across orgs. Security is an interesting one because it seems to have less of this friction, maybe because it's more clear cut what is an issue.

So I'm increasingly uncertain about what and how to test. My default for now is still to rely on ability to write basic code fluently, but I'm open to changing this perspective.

I really want to know how this existing repo AI-assisted live coding test works, with example problems.

It seems the standard data structure puzzle type thing won't be feasible if you are using an LLM.

Also the latency for these agentic coding/prompts seems like it would make the interview a bit awkward.

Anyone been conducting or taking interviews with this kind of thing with thoughts to share?

I tend to like the smaller meetups that are focused. But they often degrade in quality as they scale. A failure mode I hit several times was group circles with a louder or opinionated person eventually entering and taking the focus of the group. For large meetups that's not an issue I suppose. Break-out groups did work, but it needs some planning.

I'm surprised there's no LoRa layer or auto RL or adversarial step to reduce the stock phrases as they pop up. Is it really so hard to push these out? Or is it just whack-a-mole no matter what you do?