Same way that I would trust your review to be accurate. Because the reviewer has built a reputation for correctness.
Its not Claude doing the review. Its a human doing the review, but using Claude to do the reading. Its still on the human to ask the right questions to Claude.
For large changes that are not straightforward and include architectural decisions, I wouldn't trust Claude enough to not read most of the code myself. I'll have to read it to be able to understand it and ask about the decisions in detail anyway. And when I start to understand it, it's not uncommon to find out that the solution can be improved and simplified in many places, and after iterating, 25-30% of code disappears.
And trying to just hand-wave it to Claude, to somehow "improve it" or "simplify it", without detailed questions hasn't been very successful. It can work for some things, though.
Depends. Do you take pills that let you forget that you wrote the code so you can review that same code with fresh eyes that haven't seen that code before? Though you could just use ChatGPT to review the code that Claude wrote if that's really the issue.
This is a blog on the root cause. MCAS would be an intermediate mechanism in making you feel sick, but something must have triggered the MCAS. Thats the autoimmune response.
MCAS is the underlying condition, which is then triggered by a Covid infection. This results in an escalation of baseline symptoms, which is what Long Covid is
Last week I built Grove as the successor to my IDE. Like many, I suspect, I was struggling to coordinate multiple agents per repo recently. Cursor, Zed, Superset, Conductor, all are now following a layout centered around worktrees, but I felt like they were missing the point. I just need some organizer for my shells and a diff viewer. I no longer want to deal with a debugger, or an lsp, or code navigation.
Give it a whirl if this resonates with you! Grove is rough around the edges and was designed with my workflow in mind, but I welcome contributions to eg supporting more VCS, another package manager, or be more friendly to whatever agent you like!
Built in Rust, because why not? An Electron stack just sounds like a hassle to maintain in this Brave New World of ours.
I want this, but I do not have the experience with radio signals to build this myself without more guidance. Is there a DIY proof of concept I could lean on? How much more challenging will this be if you are in an area with overlapping FM signals from 2 transmitters sending the same signal?
That's very evil to recommend a graduate electrodynamics book to learn more about passive radar. I would suggest taking a look at Platos Republic to get some intuition on why that is. </s>
A famous quote from Carl Sagan in the marvelous Cosmos documentary where he explains atoms by slicing an apple pie until you can not slice no more because you are down to a single elementairy particle the atom.
Carl also references Plato's Republic when visiting the actual cave where Plato lived.
Carl also references books classical mechanics but not the book the parent comment mentions but earlier ones like Al-Baghdadi, Cristian Huygens, Galileo, Newton.
You can start with the radar receiver data from this 7 part DIY radar course [1] from a guy who works at a company who sell the needed chips.
Halfway in the video he mentions the MIT (or Stanford) course of a professor who recently died. That course is online and has a lot of documentation (much better than this course.
You can contact me if you want more guidance.
For passive radar you can just start with recorded data. I have access to huge amount of recordings on the Ukraine battlefield. Buying or building cheap antennas and radios is not needed for passive radar software development.
Radar was developed during the last two years of WOII, mainly in Boston at MIT and hundreds of companies each building a radar, most were deployed months later to win the war.
Development after the war shifted to Silicon Valley, founding Silicon valley and the later chip and software startups decades later.
I feel like your comment is in itself a great analogy for the "beware of using LLMs in human communication" argument. LLMs are in the end statistical models that regress to the mean, so they by design flatten out our communication, much like a reductionist summary does. I care about the nuance that we lose when communicating through "LLM filters", but others dont apparently.
That makes for a tough discussion unfortunately. I see a lot of value lost by having LLMs in email clients, and I dont observe the benefit; LLMs are a net time sink because I have to rewrite its output myself anyway. Proponents seem to not see any value loss, and they do observe an efficiency gain.
I am curious to see how the free market will value LLM communication. Will the lower quality, higher quantity be a net positive for job seekers sending applications or sales teams nursing leads? The way I see it either we end up in a world where eg job matching is almost completely automated, or we find an effective enough AI spam filter and we will be effectively back to square one. I hope it will be the latter, because agents negotiating job positions is bound to create more inequality, with all jobs getting filled by applicants hiring the most expensive agent.
Either way, so much compute and human capital will go wasted.
> Proponents seem to not see any value loss, and they do observe an efficiency gain.
You get to start by dumping your raw unfiltered emotions into the text box and have the AI clean it up for you.
If you're in customer support, and have to deal with dumbasses all day long who are too stupid to read the fucking instructions. I imagine being able to type that out, and then have the AI remove profanity and not insult customers to be rather cathartic. Then, substitute "read the manual" for an actually complicated to explain thing.
I am stumped. Am I misreading, or are the folks at Google deliberately confounding two interpretations of "world model"? Dont get me wrong, this is really cool, and it will undoubtedly have its use. But what I am seeing is an LLM that can generate textures to be fed into a human-coded 3d engine (the "world model" that is demonstrated), and I fail to see how that brings us closer to AGI. For AGI we need "world models" as in "belief systems". The AI model must be able to reason about (learned) dynamics, which I dont see reflected in the text or video.
>an LLM that can generate textures to be fed into a human-coded 3d engine
I'm not certain but I think the LLM is also generating the physics itself. It's generating rules based on its training data, e.g. watch a cat walk enough and you can simulate how the cat moves in the generated "world".
I see at least 2 axes here:
* Should access to a tool be restricted of it is used for malice
* Is a company complicit if its automated service is being used for malice
For 1, crowbars are generally available but knives and guns are heavily regulated in the vast majority of the world, even though both are used for murder as well as legitimate applications.
For 2, things get even more complicated. Eg if my router is hacked and participates in a botnet I am generally not liable, but if I rent out my house and the tenant turns it into a weed farm i am liable.
Liability is placed where it minimises perceived societal cost. Emphasis on perceived.
What is worse for society, limiting information access to millions of people or allowing csam, harrassment and shaming?
It is not clear that limiting Grok limits information access to millions of people, so I think your premise is flawed.
There are plenty of other resources that could serve the same people that Grok serves. Further, the fact that we aren't having discussions about ChatGPT or Claude as CSAM generators also suggests that Grok could be limited in ways that it isn't being limited currently.
It is not meant to save the doctors face. The very definition of FND is "doctors dont know what is wrong, but they acknowledge that your symptoms are real".
The point of giving it a name is in the second part. Its about explicitly acknowledging the limitations of medicine
Which when it leads to abuse it's saving face and when it's incompetence it's saving face.
For a competent doctor it's used too let a patient know they're doing their job and an acknowledgement of symptoms.
Unfortunately to a _lot_ of the field "catch-all" "diagnoses" (in intentionally separating these labels). It's the same as diagnosing someone with chronic fatigue. It's diagnosing via exclusion.
The difference between chronic fatigue and brain disorders being that you're more likely to get someone looking to make a "name for themselves" diagnosing or curing the latter vs the former...
A healthy, whole-food plant-based diet is linked to a lower risk of ischemic stroke, with studies showing reduced risk compared to meat-eaters. The conclusion of this paper[1] for example reads that "Lower risk of total stroke was observed by those who adhered to a healthful plant-based diet."
Additionally, researchers at Harvard found that a plant-based diet may lower overall stroke risk by up to 10%. [2]
Hey, do whatever helps you sleep at night. That's what I do. We're all going to the same place - a couple of years here and there won't do much when you're that old anyway.
Its not Claude doing the review. Its a human doing the review, but using Claude to do the reading. Its still on the human to ask the right questions to Claude.
reply