Databases and search engines have different engineering priorities, and data integrity is not a top tier priority for search engine developers because a search engine is assumed not to be the primary data store. Search engines are designed to build an index which augments a data store and which can be regenerated when needed.
Anyone in engineering who recommends using a search engine as a primary data store is taking on risk of data loss for their organization that most non-engineering people do not understand.
In one org I worked for, we put the search engine in front of the database for retrieval, but we also made sure that the data was going to Postgres.
> Anyone in engineering who recommends using a search engine as a primary data store is taking on risk of data loss for their organization.
It is true that Elasticsearch was not designed for it, but there is no reason why another "search engine" designed for that purpose couldn't fit that role.
I had one manager who got extremely excited about whatever you were working on. It was infectious and motivated most of the team including myself. He’s an innately curious person, but also whip smart and surely developed this skill deliberately.
I had another boss, a founder, who had a difficult relationship with engineering but was extremely gifted and had a great vision. I found myself highly motivated at this company as well, but for wholly different reasons. There are many paths to success.
Both startups had successful exits, and I felt as though I contributed meaningfully to both.
I give the agent the following standing instructions:
"Make the smallest possible change. Do not refactor existing code unless I explicitly ask."
That directive cut down considerably on the amount of extra changes I had to review. When it gets it right, the changes are close to the right size now.
The agent still tries to do too much, typically suggesting three tangents for every interaction.
I think that’s unnecessary waffling. Of course there are exceptions, but the prejudiced negative views that the old and the young hold of each are generally wrong.
For example, the constantly recurring critique that the music of the young is not about musicality[1] is always wrong. It's as wrong today as it was about Elvis.
I think you are wrong to see this as purely political. Women being portrayed as nude, battered, covered in semen, and so on are genuinely horrified. Such images would not be tolerated if they were sourced from a political ally.
Furthermore, I don't think that fake nudes of the US President are morally equivalent to fake nudes of minor public figures who are 99% women, even if the law treats them the same. We need to take into account the completely different lives that men and women online experience, where women are constantly subjected to sexualization and abuse.
This is one of those topics that discussion on HN is hopeless because women are so underrepresented.
They aren’t tolerated on X, people get banned for this. That’s why the whole thing is so duplicitous. x is not different from other platforms in this regard. Grok on X was also limited to paying users because of this.
The solution I like best is to "pin" issues that would cause the meeting to run long, with select personnel needing to stay late to address the pinned issue but everybody else leaving on time.
There's no substitute for leadership establishing a culture of meeting discipline. By and large, every org will follow the example leadership sets.
If leadership blesses this cutesy little five-minutes-late maneuver, implicitly accepting that meetings don't end on time, then meetings won't end on time at 5 after the hour either.
Some meetings are more important than others. So losing 5 minutes of a useless meeting is better than not going over 5 minutes for the important meeting.
Everyone wants to think their time is valuable, but this is relative.
Seeing the code that the LLM generates and occasionally asking it to explain has been an effective way to improve my understanding. It's better in some ways than reading documentation or doing tutorials because I'm working on a practical project I'm highly motivated by.
I agree that there is benefit in doing research and reasoning, but in my experience skill acquisition through supervising an LLM has been more efficient because my learning is more focused. The LLM is a weird meld of domain expert/sycophant/scatterbrain but the explanations it gives about the code that it generates are quite educational.
But since there’s grey in my beard, I’ve seen it several times: in every technological move forward there are obnoxious hype merchants, reactionary status quo defenders, and then the rest of us doing our best to muddle through,
Because some opinions are lazy. You can get all the summaries you want by searching "how I use agentic coding / Claude code" on the web or similar queries on YouTube, explaining in lots of details what's good and bad. If someone says "it's just hallucinations", it means they aren't actually interested and just want to complain.
Anyone in engineering who recommends using a search engine as a primary data store is taking on risk of data loss for their organization that most non-engineering people do not understand.
In one org I worked for, we put the search engine in front of the database for retrieval, but we also made sure that the data was going to Postgres.
reply