I've generally had better luck when using it on new projects/repos. When working on a large existing repo it's very important to give it good context/links/pointers to how things currently work/how they should work in that repo.
Also - claude (~the best coding agent currently imo) will make mistakes, sometimes many of them - tell it to test the code it writes and make sure it's working - I've generally found its pretty good at debugging/testing and fixing it's own mistakes.
Gemini weirdly messes things up, even though it seems to have the right information - something I started noticing more often recently. I'd ask it to generate a curl command to call some API, and it would describe (correctly) how to do it, and then generate the code/command, but the command would have obvious things missing like the 'https://' prefix in some case, sometimes the API path, sometimes the auth header/token - even though it mentioned all of those things correctly in the text summary it gave above the code.
I feel like this problem was far less prevalent a few months/weeks ago (before gemini-3?).
Using it for research/learning purposes has been pretty amazing though, while claude code is still best for coding based on my experience.
Also, if the current level of AI investment and valuations aren't justified by market demand (I believe so), many of these people/companies are getting more money than they would without the unreasonable hype.
Communication is not hard, it's very easy, but there are actors who's goal is to obfuscate communication and prevent others from participating.
At the end of the day it comes down to who the decision makers are and how they are incentivized to act. As a simple example - company X has product C, and they set a goal of increasing usage of feature F (of product C). Currently this feature F completely sucks and users don't want to use it - so the idea is to improve it and thus increase usage.
There are 2 ways of increasing usage:
1) Make the feature F more useful/better.
2) Force/push your users to use feature F, by aggressively marketing it, and pushing it within the product surfaces, making it non-optional, etc. and other dark patterns.
Option (1) is hard to do - it requires deep understanding of the product, user needs, the related tech, etc. It requires close tactical collaboration between product and engineering.
Option (2) is easy to do - it requires ~zero innovative thinking, very surface-level understanding of the problem, and relies purely on dark patterns and sketchy marketing tricks. You can almost completely ignore your engineers and any technical debt when following this approach.
If your decision makers are imposter PMs and marketing/sales people - they will almost always choose option 2. They will increase the 'apparent usage' of this feature in the short term, while reducing overall customer satisfaction increasing annoyance, and reducing the company's overall reputation. This is exactly how many 'growth' teams operate. Short term benefit/gaming of metrics for long term loss/reputational damage. Their success metrics are always short-term and linked directly to bonuses - long term effects of these kinds of strategies are ~always completely ignored.
The disconnect is more between long term business value, and short term benefit for the most parasitic and manipulative actors within the business.
Engineering and business value go hand-in-hand in a healthy tech/engineering business.
A business that was built on great/innovative engineering, became successful, and then got taken over by various impostors and social manipulators, who's primary goal is gaming various internal metrics for their own gain, is not a healthy business.
Apply that logic to any failed startup/company/product that had a lot of investment (there are maaaany) and it should become obvious why it's a very weak and fallacious argument.
> No one is arguing the historical & material reasons as to why Bay Area is the birthing place of many technological revolutions.
You're kinda missing the bigger picture - the fact that Bay Area was not always a tech hub, and became one at some point for various reason - which can happen in any other place (and has).
> which has systemic downstream advantages that cannot be replicated.
Seems like a very baseless and meaningless statement.
> Being surrounded by Stanford, Berkeley, etc gives the region a constant flow of world class engineers.
Except for the fact that the vast majority pf Bay Area tech talent does not come from Stanford or Berkeley, and is being outsourced at ever increasing rates.
> Theres just no other region like it and won't be for a very long time.
Yeah except for it has always been a tech hub because the term "tech hub" didn't exist before the Bay Area? I mean the first message sent over the precursor to the internet was from UCLA to the Stanford Research Institute in 1969, and the SF Bay Area having some of the first infrastructure for high-speed internet was a key factor into its position as the tech hub. Mind you this is all preceded by Hewlett Packard 30 years earlier setting the stage for the semiconductor revolution, and even this is preceded by 100 years with Leland Stanford. To much to talk about here as to why there is a unique mix of private capital, industry/government collusion, university research and development, and more that are entrenched in the region.
The makeup of tech companies employees doesn't remotely tell the full story of the advantages of the UC system, Stanford, and other universities in CA through research that feed into SV as the leading tech hub that cannot be replicated (See example of the invention of the internet above). I mean hell, 4 UC alum won nobel prizes this year alone, one of which was the chief scientist at Google's quantum AI.
But yeah sure, if we're talking in the context of "anything is possible" then yeah I concede, it can happen anywhere. Kind of a boring insight. The point is that no - it hasn't happened anywhere else to the extent of the bay area despite cities trying to for the past 30 years- and it won't happen for a very long time because of the converging mechanisms that took place over the past 100 years.
Places where technological innovation and development happen have existed long before the internet and semiconductors. The industrial revolution didn't originate or center around the Bay Area.
> The makeup of tech companies employees doesn't remotely tell the full story...
What? You made the argument that Bay Area has some kind of special access to tech talent because of Stanford - I simply pointed out that the vast majority of Bay Area tech employees are not from Stanford (not to mention many Stanford alums leave California).
> UC system, Stanford, and other universities in CA through research that feed into SV as the leading tech hub that cannot be replicated
> Places where technological innovation and development happen have existed long before the internet and semiconductors. The industrial revolution didn't originate or center around the Bay Area.
You said tech hub. By all definitions of the term the Bay Area was the first. Nor did I say the industrial revolution originated around the Bay Area?
> What? You made the argument that Bay Area has some kind of special access to tech talent because of Stanford - I simply pointed out that the vast majority of Bay Area tech employees are not from Stanford (not to mention many Stanford alums leave California).
You tend to do this a lot. "Many Stanford alums leave California" and "talent is being outsourced at ever increasing rates". Just vague generalizations that offer nothing to the overall conversation.
I made the argument that being close to these universities gives the region a constant flow of world class engineers and researchers. This is true whether or not they work for Bay Area tech companies you understand this right? Regardless, out of the reported feeder schools into tech 5 out of the top 10 are California universities.
You just named universities from 5 different states/regions? Please keep up.
> And several google/deepmind employees from/educated in UK won a nobel prize in 2024... what's your point?
They weren't from the same school? The UC system altogether has over 150 nobel prizes and thats before including private institutions like Stanford, Caltech, USC, and others. Thus exemplifying the unique system dedicated to research and technology consolidated in one region..
> It was more true (but still very boring) 10 years ago, not anymore.
Going to be honest man from interacting with you it seems like you have a chip on your shoulder about the bay. I don't even live there I live in LA. It shouldn't bug you to point out the objective fact that the unique confluence of geographic location, surrounding education system and research institutions, compounded wealth from prior historical industrial/technological windfalls, makes SV the premiere tech hub that is consistently on the forefront of burgeoning technologies - not by accident.
Are you also confused as to why NYC is the finance capital of the world? Do you think Toronto could usurp it one day if they just try hard enough?
No, you said tech hub. Which is short of 'technology hub', which is not just limited to mobile apps.
> You tend to do this a lot. "Many Stanford alums leave California" and "talent is being outsourced at ever increasing rates". Just vague generalizations that offer nothing to the overall conversation.
Those aren't generalizations, those are very specific statements, which go directly against your vague generalizations ('oh but there are good universities in the area for tech talent therefore its impossible to replicate'), and which you apparently can't disagree with because they are obviously true.
> I made the argument that being close to these universities gives the region a constant flow of world class engineers and researchers.
Nope, what you said is that because these universities are located in that area - no other region could possibly compete. And I gave you very specific examples of why that's not true.
> You just named universities from 5 different states/regions? Please keep up.
Yeah.. some of the leading universities for tech talent in the world... which are not in California... (which according to you is impossible)... please keep up.
> makes SV the premiere tech hub that is consistently on the forefront of burgeoning technologies
I never said SV is not a major tech hub. I actually said the opposite. What I disagreed with is your baseless assertion that no other region could possibly compete, or that tech companies have to be in SV to succeeded (which is obviously false, and which I see you shifting the goalposts on now)
> Are you also confused as to why NYC is the finance capital of the world?
Maybe you should rewind to back when NYC wasn't a major finance hub, then apply your same reasoning - 'NYC couldn't possibly become a finance hub, because London is the finance hub'.
Your arguments are self-contradictory and not logical.
> "You're kinda missing the bigger picture - the fact that Bay Area was not always a tech hub, and became one at some point for various reason - which can happen in any other place (and has)."
Lol are we children now? No, YOU literally said tech hub.
> Those aren't generalizations, those are very specific statements, which go directly against your vague generalizations ('oh but there are good universities in the area for tech talent therefore its impossible to replicate'), and which you apparently can't disagree with because they are obviously true.
No, they are generalizations. I have given you myriad examples as to why the UC system and its integration with research and development is unique and doesn't exist anywhere else in the US let alone can be replicated. "Many Stanford alums leave California" means nothing to the overall point (despite 70% staying in CA). Yes, some people from one university leave California leave? Yes? And? "Talent is being outsourced at ever increasing rates". Yes, and? Talent is being outsourced at ever increasing rates everywhere in the US. Outsourcing talent has going on for a long time. Again, means nothing to the overall point.
> Nope, what you said is that because these universities are located in that area - no other region could possibly compete. And I gave you very specific examples of why that's not true.
You did not? You named universities from 5 different states and/or regions. I am actually beginning to be concerned. You understand the difference between what I'm saying right? The 5 schools you named have been around forever.. They haven't replicated what the UC system and surrounding schools have create in the Bay Area. So your examples are stupid?
I didn't even say leading universities in tech can't exist outside of California? What are you even saying anymore?
> What I disagreed with is your baseless assertion that no other region could possibly compete, or that tech companies have to be in SV to succeeded (which is obviously false, and which I see you shifting the goalposts on now)
No other region right now is competing - or can compete. I conceded to your overall vibes-based opinion that "anything can happen" and that yes, in a miraculous set of circumstances held over 50+ years that some region could usurp the Bay Area with tech. I then continued with historical and contemporary examples as to why that won't happen anytime soon.
> Maybe you should rewind to back when NYC wasn't a major finance hub, then apply your same reasoning - 'NYC couldn't possibly become a finance hub, because London is the finance hub'.
Please reference my last response. Yes, New York became a major financial capital (and competitor to London) after 150 years of massive historical circumstances (WW1, Bretton Woods, etc). Perhaps this could happen to the Bay Area in tech, sure - but these aren't happening separately in a vacuum. Whilst the title of financial capital of the world traded hands between London, NYC, and even Tokyo in the 80's, one thing stayed constant, and that is the tech industry remained in SV.
There is no NYC in the 20's equivalent to the Bay Area's London in this equation.
> Your arguments are self-contradictory and not logical.
They are not. Here is my argument in a nutshell: Silicon Valley became - and remains - the global tech hub thanks to a unique mix of top-tier universities like Stanford and the surrounding UC system, early government investment in semiconductors, a deep venture capital ecosystem, and a culture of innovation and risk-taking. Other regions domestically and internationally, have struggled to catch up because they lack the decades of compounding infrastructure, talent networks, and startup experience that can’t be quickly replicated.
Yes and I explained with walls of text of historical, geographical, socioeconomic examples how that is true and your disagreement boils down to "but anything can happen", which is boring in a discussion, so its pointless to continue. Yeah and Des Moines could become the global finance capital of the world, there is nothing you can say to allude otherwise because we don't know what could happen in 500 years.
> location you're physically sitting in doesn't really matter
Of course it does.
The benefits of proximity to business clusters [1] is well researched [2]. There is no evidence remote work has dampened that tendency; if anything, as evidenced by AI, the effect seems to have increased.
You're linking to pre-covid studies, that mention some types of benefits (for specific reasons like logistics benefits for businesses relying on physical materials/goos, or physical access to people for the purposes of networking), for some kinds of industries, and also mention that these benefits are not seen for some industries.
> Sometimes cluster strategies still do not produce enough of a positive impact to be justified in certain industries.
Let's take a step back and look at the fundamentals of a tech company who's employees are remote - what are the specific benefits of having a San Francisco office?
I'm linking to studies summarising a century of work. There is no evidence Covid changed this.
Exhibit A for Covid having not changed this is the continuing supremacy of Silicon Valley (tech), Shenzhen (manufacturing) and New York (finance) as industrial clusters that others have tried to replicate (everyone, America and Miami, respectively) and failed.
> Let's take a step back and look at the fundamentals of a tech company who's employees are remote - what are the specific benefits of having a San Francisco office?
Proximity to investors. Proximity to customers. Proximity to a skilled employee pool. Proxomity to acquirers. (A lot of deals happen at cocktail parties and ski trips.)
By the way, I'm not arguing anyone needs an office. Just people physically and and proximate to the cluster.
> Exhibit A for Covid having not changed this is the continuing supremacy of Silicon Valley (tech)
You mean like when China built chatgpt 4 in a weekend and open-sourced it for giggles?
> Shenzhen (manufacturing)
..or you mean how US manufacturing 'clusters' almost completely disappeared/replaced by Chinese ones?
> Proximity to investors. Proximity to customers. Proximity to a skilled employee pool. Proxomity to acquirers.
Right, cause you have to physically pet every investor on the head to fundraise, your remote employees must be in san fran cause network latency interferes with their windows remote desktop workflow, and, for some reason, you have to be physically close to your customers when you're selling your web-only llm wrapper saas.
> You mean like when China built chatgpt 4 in a weekend and open-sourced it for giggles?
DeepSeek R1 is an amazing feat. It's not at the same level as other large frontier models from American companies, just close enough to make them sweat.
> ..or you mean how US manufacturing 'clusters' almost completely disappeared/replaced by Chinese ones?
The value of goods manufactured in the US has never been higher. US manufacturing focuses on goods at the top of the value chain: jetliners, cars, semiconductors, medical scanners, and other advanced electronics. These tend to cluster in a few places - for example, Long Beach is a hub of space and avionics manufacturing, Texas has the "Silicon Prarie," and Boeing in Everett is one of the major employers in the region. Manufacturing has disappeared as a share of GDP, but that's not because we make less stuff.
> Right, cause you have to physically pet every investor on the head to fundraise, your remote employees must be in san fran cause network latency interferes with their windows remote desktop workflow, and, for some reason, you have to be physically close to your customers when you're selling your web-only llm wrapper saas.
You sound sarcastic, but YES. You do generally have to physically be present to make deals. It is obviously theoretically possible to run a world-leading software company fully remote. Despite that, most of them are in-person at least a few days a week. If you want to take advantage of SV's easy VC money, you absolutely have to be present.
Companies are not purely about the numbers. A lot of business is imprecise and heavily dependent on things like just plain LIKING the people you're in bed with, and unfortunately there is no substitute for being in the same room as someone to make a decision like that.
> Manufacturing has disappeared as a share of GDP, but that's not because we make less stuff.
We assemble. The actual parts are largely made overseas.
Because location matters, assemblers in China are able to do better work at a much lower price, see every Chinese EV company, or Chinese drone companies.
Heck in China you can buy a competent Chinese EV motorscooter for less than a kids bicycle in America.
> It's not at the same level as other large frontier models from American companies
Cool story
> The value of goods manufactured in the US has never been higher... Manufacturing has disappeared as a share of GDP, but that's not because we make less stuff.
You're seriously going to try to argue how US manufacturing (which was the greatest share of global manufacturing by far) didn't decline, to support a point about how China (Shenzhen) is apparently an unreplicable manufacturing hub due to 'cluster effect'? It's funny that you don't see the contradiction. For the record, US manufacturing as a share of global manufacturing has significantly declined over the years. [0][1]
"
> The United States' share of global manufacturing activity declined from 28% in 2002, following the end of the 2001 U.S. recession, to 16.5% in 2011
> China displaced the United States as the largest manufacturing country in 2010
> Manufacturing output, measured in each country's local currency adjusted for inflation, has been growing more slowly in the United States than in China, South Korea, Germany, and Mexico
"
> You do generally have to physically be present to make deals.
If you need to be physically present for a meeting, you make a trip. There is absolutely zero benefit to living in close proximity to investors the rest of the time.
> It is obviously theoretically possible to run a world-leading software company fully remote.
It is obviously not just theoretically possible, and many companies do so.
I am not going to link you benchmarks or revenue numbers. You can find those yourself, if you actually care about being right.
> It's funny that you don't see the contradiction. For the record, US manufacturing as a share of global manufacturing has significantly declined over the years. [0][1]
Yes, because China is _cheap_ and _dense_ and has a billion newly-minted middle-class members. Do you expect them to import everything from the US and just ignore the vast labor pool within a few metro stops of any given factory?
> to support a point about how China (Shenzhen) is apparently an unreplicable manufacturing hub due to 'cluster effect'?
The Pearl River Delta, which Shenzen is part of, has almost 90 million people and a world-class transit system. It's across the water from Hong Kong, a global financial center, and is bordered by factory-filled cities on the other side.
Yes, that makes it nearly impossible for other places to become Shenzen. Even within China it's special.
> If you need to be physically present for a meeting, you make a trip. There is absolutely zero benefit to living in close proximity to investors the rest of the time.
Right, because if you're doing business you can get by with a single investor meeting a year, right? There's no downside in time lost, money spent, ease of access, etc.? You think there's no benefit to, say, playing tennis on weekends with your buddy from college who now works at a VC?
> You're seriously going to try to argue how US manufacturing (which was the greatest share of global manufacturing by far) didn't decline
Why the hell does it matter what percentage of global manufacturing is done in the US? You cannot ask the average American (one of the wealthiest people in the world) to work in a sweatshop making T-shirts. You cannot ask the average American to work for minimum wage tightening screws in iPhones.
You can, as it turns out, ask them to work a robotic assembly line to build a car or weld on a jetliner - because you can pay them much more, and because there are enough of them in an area to run a factory. Aggregation benefits are even more important for manufacturing than they are for software.
> Yes, that makes it nearly impossible for other places to become Shenzen. Even within China it's special.
You're skipping n = 1 and jumping straight to k. How did modern Shenzen become what it is? Through specific reasons like infrastructure investment, or because it was always a 'manufacturing cluster'? By your logic Shenzen must have been the manufacturing hub of the world since before the dawn of time... since it's 'impossible for any place to become Shenzen'.
> Right, because if you're doing business you can get by with a single investor meeting a year, right?
Because the only way to meet and communicate in 2025 is in person?
> There's no downside in time lost, money spent, ease of access, etc.?
All of these are better remote/digitally in most cases.
> You're skipping n = 1 and jumping straight to k. How did modern Shenzen become what it is? Through specific reasons like infrastructure investment, or because it was always a 'manufacturing cluster'? By your logic Shenzen must have been the manufacturing hub of the world since before the dawn of time... since it's 'impossible for any place to become Shenzen'.
Sure, any region in a rapidly developing and very dense country, with a large preexisting financial hub nearby, 50 years ago, could have become Shenzen. There was only one of those, and consequently there is only one Shenzen. How far back do you want me to go? Should I discuss the agglomeration effects enjoyed by the Han Dynasty?
> Because the only way to meet and communicate in 2025 is in person?
Why don't you try using that logic on someone you're convincing to give you a large sum of money and report back? The real world does not work this way, and that is why there is still only one Silicon Valley. I've made this point several times now and can point to the status quo to back it up.
> All of these are better remote/digitally in most cases.
I work partially remote. I intentionally schedule my meetings in person because I find that to be significantly better than a video call. I am definitely not alone, and for startups it is even more advantageous to physically be in the same room as the entire rest of the company.
> There was only one of those, and consequently there is only one Shenzen.
Really? There was only one rapidly developing, densely populated region with a financial hub nearby (why does the proximity of finance even matter?), in the entire world in the last 50 years (why 50 years)? Are you sure about that? (you are 100% wrong)
> I intentionally schedule my meetings in person because I find that to be significantly better than a video call.
Sounds like a you problem. Also the fact that you are 'partially remote' and you still schedule your meetings to be in person tells me: a) you do not have very many meetings b) you work with a fairly narrow scope of people who you can physically get into the same room on a regular basis.
I meet with founders, investors, tech leaders, and many various stakeholders on a regular basis. It would be absolutely IMPOSSIBLE to have these meetings in person.
> for startups it is even more advantageous to physically be in the same room as the entire rest of the company.
If you say so, but the record number of fully remote startups that keep popping up at ever increasing rates says the opposite.
> Why don't you try using that logic on someone you're convincing to give you a large sum of money and report back?
Been there done that. If you need to meet in person to make final agreements/sign you can travel. Vast majority of communications/negotiations around fundraising and related happens digitally today.
> There was only one rapidly developing, densely populated region with a financial hub nearby (why does the proximity of finance even matter?
Because if you want to build factories you need capital. This is not rocket science. Much easier to get a loan when there are a billion bankers across the bridge.
Yes, there was only one place with all the ingredients to become Shenzen. Believe it or not, global financial centers are not commonly found in developing countries. Why don't you propose some alternatives, I'll wait.
> Sounds like a you problem. Also the fact that you are 'partially remote' and you still schedule your meetings to be in person tells me: a) you do not have very many meetings b) you work with a fairly narrow scope of people who you can physically get into the same room on a regular basis.
I have plenty of meetings, and I don't know what you're smoking if you think that more than a large conference room's worth of people could all participate in a meeting. Neither of these disqualifies what I'm saying.
> If you say so, but the record number of fully remote startups that keep popping up at ever increasing rates says the opposite.
And how many of these are becoming wildly successful, compared to in-person companies located in desirable cities?
> Vast majority of communications/negotiations around fundraising and related happens digitally today.
[citation needed]
Also it doesn't count if the numbers get worked out over email but the handshake was in person.
This is the opposite of true. It's actively wrong. Location is almost everything; people move to financial and tech centers for a reason -- it matters where you are and who you know.
> where you are and who you know are very different things
Different but related. Getting a purposeful introduction involves a lot more friction than being invited to someone's home for dinner with their colleagues and contacts.
This is so funny to imply that you (living in East Jesus, Texas) have a better or similar opportunity to me (living in SF) in making more relationships and connections to AI related companies, engineers, investors, customers, acquirers, scientists, etc.
I live a lot further from SF than Texas, yet I've been working fully remote for SF tech companies (among others) for 10+ years.
If I need to meet someone in person, I make a trip (~few times a year)
It's true that I can't brownnose/service random tech talking heads in person on a daily basis tho, which is what I assume you mean by 'relationships and connections' lmao
Okay so what you're doing is contradicting the objective advantages/benefits of living near the epicenter of a specific industry with a purely anecdotal example of 10+ years experience in jobs from said epicenter, with the expendable income to travel (domestic/international) for in-person meetings, then defining networking to a disingenuously generalization because it reinforces your opinion.
What if I were to tell you that you can make meaningful relationships and connections w/o "brown nosing/servicing" and its easier to do so in the center of a specific industry?
I'm giving you a specific example of why it's not necessary to be in any particular location to work in tech, or network, collaborate, communicate with other tech people.
Directly contradicting your baseless assertion about how you have to be in SF for those reasons.
Literally a specific, physical example and you're talking about 'defining networking to a disingenuously generalization' ...
I truly don't know what to even say. It is futile to relitigate the uncontested reality that there are a wide array of significant advantages to living near cultural, technological, and economic centers that are adjacent to your profession. You live alone in this area where this isn't obvious. I'd even posit you would be more successful than you already are if you lived closer.
The fact that he is even going to jail, or that there was a trial at all, is amazing. In Canada, top-level corruption like this just gets covered up by RCMP (who are directly top-down controlled by PM) - many cases of this.
He has half a dozen court dates set for other stuff related to corruption/money/....
Assuming he's losing the appeal on this particular case, he will have been sentenced for scheming with a convicted murderer (Lockerbie amongst other things).
If convicted, that person will be guilty of criminal actions together with a foreign dictator and his terrorist in chief.
Not exactly stealing gums.
The case is of particular seriousness and he's a convicted person, repeat offender.
Would something as serious be put under the rug in other democracies? I'm not so sure. If Justin Trudeau is found accepting money from a bunch of Taliban involved in weapons trafficking, would the RCMP turn a blind eye?
(Why do I say "if convicted"? He appealed, so he is innocent until proven guilty. Why is he in jail? In large parts because his political party lobbied for this type of sentences. Leopards did eat his face)
> If Justin Trudeau is found accepting money from a bunch of Taliban involved in weapons trafficking, would the RCMP turn a blind eye?
RCMP turned a blind eye to multiple corruption scandals involving bribery, fraud, embezzlement of public funds, etc. under Trudeau and his government, and helped cover them up. That is just the tip of the iceberg when it comes to corruption within the RCMP - there is a long list of nefarious and straight up illegal shit they have done over the years.
One that I've noticed recently is that we had a housing "crisis" up until prices actually sort of started dropping, and now all the coverage is about the plight of condo developers. Thankfully we have the former mayor of the most expensive city in Canada as the housing minister, chosen over the MP for Beaches who actually seemed to give a damn.
That's arguably negligence (though such blatant negligence is evidence of corruption), but there are corruption scandals involving straight up fraud and embezzlement of public funds by the top levels of government almost every year.
Also - claude (~the best coding agent currently imo) will make mistakes, sometimes many of them - tell it to test the code it writes and make sure it's working - I've generally found its pretty good at debugging/testing and fixing it's own mistakes.
reply