Raised multilingual here (as in father spoke one, mother spoke another, living abroad and US back and forth). I don't know about the stronger social ties but I have found that thinking in a different language helps me get to sleep easier. There are times when I'm spinning around in webs in English (work, life etc) at night, and when I switch over to Spanish thoughts I fall asleep easier.
Maybe just stuff like that is enough to make a difference.
Switching into another language also helps if you are stuck in an environment where you do not want to pay attention (e.g. on a bus with blaring ads that you can't mute or with a rude neighbor yapping on their phone).
I grew up speaking multiple languages. My monolingual friend once asked in which language I dream, and I said - "not sure, I think in all three different ones I'm currently fluent". "But how do you know?", he kept pressing. "Ah, well, they come with subtitles", I joked. But since then I often wonder, how do we recognize a language in our dreams?
I think my dreams use semantic vectors that come with a tag saying they came from sensory input even though they didn't.
I am mostly monolingual but I would expect them to come with a language tag too. I believe a dream about Bob talking about cats in Spanish would directly activate your neural network like V_cats + V_spanish + V_bob_is_talking without activating the parts that would decode auditory input into that semantic vector.
I work in AI, both building at a large company and consulting on the side. My manager (of two months) uses claude to reply to everyone in Teams and emails, usually filled with nonsensical slop. I believe in its potential when applied correctly but also am realizing that it's unlocking an entirely new kind of fraudster.
It's very easy to build a basic code review tool.
It's hard to build one that developers won't ask you to turn off because of false positives (or one that will miss your next escaped bug)
I think if all the tool does is run a claude code level /review skill (which all developers should definitely run before they even open a PR) then isn't this a bit of a review theater? Just a guardrail to those developers who don't run a /review-triage-fix skill in /loop before they take the PR out of draft?
I wonder how many PRs in the world got to production where several developers commented on each other's code, and none of them read anything, just used their gh cli / MCP to post / answer comments / fix issues on their behalf.
There is going to be an exponential growth of code generated, and you can't escape AI code review, but also there is no real difference between having Claude Code write the code and review itself locally, vs communicating with itself via a slow and downtime prone medium of "PR comments"
tl;dr - without any human in the loop reviewing the AI code review, or skimming to see what the AI code review missed, there is no real reason to use a "code review" you can just run it as part of the CI/CD and hope AI won't miss anything (according to my linkedin feed, there are people out there who really thing this way...)
Yes! Where it gets really interesting is the scenario in which every developer has their own unique review skill/workflow, so the reviews end up being different than you running it yourself, but nobody is reading them still.
I think that in most cases you either agree on a PR comment or you don't. But it has to leave a mark in PR. This is how we do reviews, ignoring PR comment is one of the worst offenses one can make. I don't let it go.
For sure it was overkill/not the most efficient approach - really I was more just curious if it would work. The answer was "kind of", but even that is pretty amazing. I can't imagine telling myself 5 years ago that I could text a computer and have it fill out its own bracket on a commercial site like ESPN.
its going to be cool when you put in your todo list in the morning that you need to fill out your espn bracket and by lunch your agent will have 3 different versions ready for your review
Really cool idea. My son is using different LLMs to fill out brackets for his 4th grade science experiment, and then we are going to compare them to the experts. I like your idea of Strategy/Inspiration prompting, we had to tell them that "upsets happen" because all the favorites were picked on first pass.
Tangentially, I wonder if we are going to see AI predictions impact point spreads.
Maybe just stuff like that is enough to make a difference.
reply