opdahl

So because he is responsible for a breakthrough he de facto becomes a trustworthy person? How does that connect?

Why do you say that? I'm unfamiliar with Heritage Auctions.

Does anyone know how well this scales? I assume it just doesn’t make sense to actually make one of that size when they are testing out the concept.

Since you specifically were wondering if something like this exist, I feel okay with mentioning my own tool https://keenious.com since I think it might fit your needs.

Basically we are trying to combine the benefits of chat with normal academic search results using semantic search and keyword search. That way you get the benefit of LLMs but you’re actually engaging with sources like a normal search.

Hope it was what you were looking for!

Claude with location access is now an amazing traveling companion. Sharing my experience of using it in Hong Kong in an area I knew nothing about. The best thing is, is that it doesn’t ruin the experience with images etc that in my opinion spoils the locations.

That is very unfortunate to hear.

Then why are you posting a comment here at all? Just be silent if you can’t handle replies to your unsolicited comments.

Isn’t this supposed to be a short technical blog? Why does it seem like they’re a salesman and it’s a sales pitch?

> "We are generating more code than ever. With LLMs like Claude already writing most of Anthropic’s code, the challenge is no longer producing code, it is understanding it."

The first sentence already is obviously AI generated, and reading through it it, it is obviously completely written by AI to the point of it being distracting.

I understand the author probably feels that AI is better at writing than they are, but I would heavily recommend they use their own voice.

I’ve personally started to try to think about the points someone prompted an AI to generate some text (the actual thoughts of the author) so that I can more easily skim past the AI generated slop such as: "… you’ll get the env setup, required services, and dependency graph with citations to README, Dockerfile, and scripts, so you can hit the ground running".

Interesting. Why do you think that deleting all records of you would be worse?

What makes you believe this was written by an LLM?

I think it really depends on the use case. It is well known that most users really only look and engage with the top few (1-3) results in a search. If you can get the most relevant result from position, let’s say 7 to 2, that can have a big impact on the user experience. And I know they market this for RAG, but I think that’s just marketing and this is as relevant for traditional search.

I personally tried it and I felt it way more confusing to use compared to using Cursor with Claude 3.7 Sonnet. The CLI interface seems to me more to lend itself for «vibe coding» where you actually never work and look with the actual code. That is why I think Cursor and IDEs are more popular than CLI only tools.

Together with 3.7 Sonnet. And the claim was that it is rapidly gaining ground, not that it sparked initial interest. I still don’t see much proof of adoption. This is actually the first I’ve heard about anyone actually actively using it since its launch.

> Claude Code (neither IDE nor extension) is rapidly gaining ground

What makes you say that? From what I’m observing it doesn’t seem to be talked much about at all.

I’m a bit confused about the naming of the model. Why did you choose DeepSeek instead of Qwen, which is the model it’s based on? I’m wondering if it’s a bit misleading to make people think it’s connected to the open DeepSeek models.

You reject that peoples personalities are shaped by their environment? What if instead of focusing on location but instead focused on time period. Do you think there would be behavioral differences between a child born to a middle class family now compared to one 1,000 years ago? What about 10,000 years ago?

Rejecting the premise that the environment shapes who we are and the type of people we become sounds extremely ignorant of the realities of history.

Hi tmnvdb, since you seem to love these super smart LLMs I thought it would be fun to have openais o3-mini-high analyze your recent comments in contrast to the Hacker News Comment Guidelines. Here is the output it gave me, hope it helps you:

------

Hey, I've noticed a few things in your style that are both strengths and opportunities for improvement:

Strengths:

- You clearly have deep knowledge and back up your points with solid data and examples.

- Your confidence and detailed analysis make your arguments compelling.

Opportunities:

- At times, your tone can feel a bit combative, which might shut down conversation.

- Focusing on critiquing ideas rather than questioning someone's honesty can help keep the discussion constructive.

- A clearer structure in longer posts could make your points even more accessible.

Overall, your passion and expertise shine through—tweaking the tone a bit might help foster even more productive debates.

------

Just reply here if you want the full 500+ words analysis that goes into more detail.

This is super cool and something I’ve been waiting on. Would be interesting to intersperse these thinking steps into token generation. What would be the effect of adding lets say 5 thinking «thoughts» for every 50 generated tokens?

Going to be very interesting to see how the Japanese people react to this. The service the taxi drivers provide when you take the taxi in Japan is on another level, such as waiting for you with the open door and closing the door for you as you enter. A driverless car will never be able to copy that. Japan also has very good public transportation reducing the need for a car for day to day travel so cost might be less of a factor.

I visited Sokcho a few months ago! I agree with you, it just has such a nice and chill vibe that makes you be at peace, and lot's of interesting history in relations to North Korea. It was also really nice to go for a bike ride around the big lake that is there.

You have to click the Sources. It definitely was a search.

There are quite a bit of AI for academic researching tools out there that are generating quite a bit of revenue or being bought up by academic publishing companies. You also have dedicated copy writing and article writing tools that basically automate (read plagiarize) the entire academic writing process.

You should check these guys out. They actually do it (rack, not hosting ML models) and it seems to me to be pretty elegant: https://www.macstadium.com/blog/m4-mac-mini-review

This seems like one of the best times to do it as long as you get your own monitor. You will probably be set for 10 more years with this thing.

Actually I tried this myself and it just failed horribly. Getting the wrong dates, citing old SEO blog spam and basically not finding anything that fit my criteria. When I asked for it to go more in depth it again failed to verify and misjudged the dates by one year.

You can take a look for yourself here: https://chatgpt.com/share/67245f76-bf88-8012-b72d-703beed088...

That is what Google makes in less than half a day by selling ads. It’s a rounding error on their monthly revenue.