That does not match my experience. Composer 2 was fantastic for my uses, and I hit Composer 2.5 with some very difficult things last night, which it handled fast and effectively. I don't really care about benchmarks. I care about practice, and in practice, it's been very very good for me.
I've been using cursor for over a year for my personal projects. At work, I use Claude Code, and so I've been wondering if I'm missing something in the other agents.
Over the last week, I tried out two other agents on my personal projects: dirac and forgecode, after seeing impressive results from both of them on terminal bench.
After a good amount of testing, and over $100 in open router spend, I'm back to cursor.
I really liked forgecode the best, and it feels better than claude code, but cursor definitely feels best to me. Composer 2.5 is fast and effective, and it makes a huge difference. I was running `forge` with Opus, and it was taking dozens of minutes to do things, and the feedback loop was so slow.
The previous version of composer was also much faster, and it makes a difference. Maybe people like context switching, but I prefer to stay focussed on the task in front of me, and I'm reviewing the code carefully.
I think that's a pretty good moat. I was ready to end my subscription a week ago, and now I'm back after learning the grass is not necessarily greener on the other side of the fence.
Not comforting at all, in fact I would find it aggravating. Yet to imply that means this is somehow a cold and callous take is what I take an issue with because it ignores the vast majority on the other side of the fence, and the economic windfall and quality of life improvement for the majority. The last thing you want to be is like Europe or any other country that is regulating their way out of the loop. You think there will be suffering if AI continues to roll out? imagine if we stop. You want Xi to chuckle at your naïveté and build out enough power to leverage the entire global economy to bend to its will?
I didn't imply anything. I just called out the emotional reality. There are a lot of externalized pain in the world today, and little recourse to addressing it. You can try telling people that they are naive and need to look at the big picture, but you might not see much success at getting your point across.
Very fair. My goal isn’t to say pain doesn’t matter, it’s to say policy to change course that would disadvantage more people than it would help is doing more damage than good. We shouldn’t let our empathy cloud judgement as hard as that is as humans. Addressing pain, like people fighting to do data centers right (sans people trying to simply stop any data center construction) and ensure impact to local life is not made worse are good efforts because it imperils nothing. Companies will just optimize within regulatory framework (for the most part) and so grassroots movements to change the things we can are great.
It sounds like this has a pretty falsifiable claim here - is the revenue attributed to a tax thing? Then it's clearly not attributable to code.
I agree that the macro picture would speak for itself. Can you point to any macro level detail that is indeed cleanly showing benefits from increased productivity from LLMs?
At the end of the day, LLM slop PR spammers are essentially adversarial actors. Git hooks are ultimately a tool for good faith developers within a given community (your team, your company, your regular contributors) in maintaining good hygiene and avoiding lapses into preventable mistakes. That's true for all CI, too.
And the truth is, too, that it's super easy for an LLM agent to run a build and tests. Good faith contributors using LLMs will never open PRs that don't build not because they're willing to "go the extra mile" and do manual work, but because they give the slightest fuck and have any respect or consideration for the humans they're working with.
LLM spam presents a different problem than any of that stuff was meant to solve. It's a malicious act, and you're right that tooling that burns the defender's compute can't be a solution. :-\
Those things cost resources, and now you're introducing a new attack vector: open up a bunch of shit PRs, burn a lot of cash for the target organization.
You're right. It doesn't solve for all scenarios and doesn't block malicious actors.
I do believe, however, that it would have a meaningful impact on the "drive-by" PRs that keep being used as examples; the thoughtless, throw-spaghetti-at-the-wall PRs that do not have malignant intent behind them.
Many large OSS projects would have the resources to eat that cost with Donors, Sponsors, and OSS hand-outs. That's why I clarified in my original post because I know this is not a general solution.
The problem is you can get the LLM to iterate until it compiles and lints and even passes LLM review, but will that actually improve the quality of the contribution or just produce more line noise to mechanistically meet criteria?
To large complex projects often the kernel of an idea is the core value of a contribution, and it can take a lot of iteration to figure out how to structure it. Token bashing until CI is green does nothing to ensure the best approach is selected.
> The problem is you can get the LLM to iterate until it compiles and lints and even passes LLM review
Worst of both worlds with this, if you're doing it in a github workflow. You wind up effectively paying for the testing/validation layer of someone else's irresponsible LLM use.
For sure, but that's not what I was referring to in my posts. I'm specifically referring to the callout that the contributions are so low quality they don't even pass linting or compile.
I could have been more explicit on that nuance, I suppose.
That's why you sandbox. You can mitigate most low-hanging DoS fruits by running your server side hooks in a per-tenant cgroup that limits CPU and memory usage. One tenant per public key for trusted contributors, and one general-purpose tenant shared by all new/unknown contributors.
Can't you prevent pushing from the client side with pre-commit hooks? I would expect a hook to fire on the developer's computer that prevents them from even committing/pushing (unless they nuke the hook in their local repo copy).
You have to manually install hooks in your local repository. They aren't propagated as part of the repo. Git has intentionally made hooks require a very explicit opt-in.
Libraries also do a lot more than just provide books. $35 per resident per year for everything that libraries do provide is forking cheap, and we would be greatly impoverished if they were to disappear.
But my point above wasn't about whether that number is high or low. It's that the price of books is paid by us, even it's funneled through taxes and librarians.
I think many men don't even understand what emotional regulation looks like. They tend to spend much of their time disassociated and thinking that it's normal. I tried speaking to my father about emotional health and he thinks it's about being happy, while simultaneously being unable to consider the possibility that he got it wrong, thus demonstrating the point.
There is a lack of emotional health across genders, but on average, I think women are further along than men, simply because they're able to recognize that they are emotional beings much more often than men are.
If talking about a topic made one skilled at or reflected skill, millions of men would be star quarterbacks.
At a macro scale men and women often have different interests. They often cluster around different skillsets because their interests channel them into different activities. But emotional self-awareness isn't an activity, it's an aptitude that fundamentally both men and women exercise (or don't exercise) with similar frequency in day-to-day life. But because women tend to pursue more interpersonal relationships and discussions, they are more adept at the vocabulary, the way men know the vocabulary and rules around football. But, again, it doesn't follow that talking about something makes one more skilled at it. You can juggle tons of relationships and engage in endless discourse about emotional and mental health without having much if any meaningful emotional self-awareness. People with vulnerable-type NPD do this, and at the extreme end the condition is basically predicated on lacking the capacity for a self-awareness most other people, including isolated men, take for granted.
Relatedly, after adjusting for income and social status, it's notable that not even psychologists and therapists have significantly lower divorce rates. That really highlights in my mind that not even an in-depth, systematic, rigorous study of something necessarily makes one more adept at it's exercise, nor, apparently, more likely to meaningfully pursue and develop the skill. Though, presumably they're more adept at judging and analyzing others' emotional awareness and skill given it's the skill they actually apply in their occupation.
I don't see how we are disagreeing. Emotional self-awareness is an aptitude, one that is fundamentally experiential, and so talking about it is inherently difficult. I agree that many people who talk about it are not necessarily experiencing it, including therapists and psychologists, especially if they are using lots of abstractions.
I'm a man who has worked on my own emotional health very intentionally as an adult. I've found there are lots of ways to understand and engage with your own emotions, and they can seem contradictory if you're not thinking experientially.
But I've never found someone who behaves with high emotional awareness that doesn't have any language for describing their experiences. They can talk about it very differently from other people. There is a huge multidimensional possibility space for that.
> But I've never found someone who behaves with high emotional awareness that doesn't have any language for describing their experiences.
There's potential selection bias here, though. It's more difficult to identify people high in self-awareness who aren't inclined to discuss their own emotional experiences, unless you happen to have frequent, close interactions with them. It's like when people assume learning languages is easy based on their experience meeting people from around the world who speak their language. But you're much less likely to interact with immigrants and travelers who don't speak your own language, if only because those people aren't inclined to engage with people with whom they can't or aren't interested in communicating.
My experience (often unfortunate) tells me that there are many behaviors that masquerade as self-awareness and other reflections of inner state, but don't actually reflect what we presume it does. For example, the stereotype is that women are naturally more nurturing. Nurturing is a concept that encompasses many dimensions, and it conflates internal motivations and feelings with outward behaviors and practice. We presume nurturing implies empathy and selflessness, but there are of mothers who by all appearances (and in fact) are great nurturers, but whose internal mental experience is bereft of those qualities. They're good nurturers because ultimately we can only judge nurturing by the outcome, and it's easy to presume a naturally patient person adept at applying good parenting practices possess the inner state we associate with nurturing. Even children of such people may not realize this, depending on their own capacity for emotional discernment.
Concepts like empathy, guilt, etc, are tricky. Is a person quick to apologize driven by guilty feelings and concern for other's internal state, or are they merely adept and eager at identifying social cues and applying social norms?
In principle women could be, as a group, more likely to possess a greater capacity for and to develop self-awareness. But history and feminism and racism tells me to be highly skeptical of something like this. While biologically it's possible (and I wouldn't at all be surprised), it's not self-evident to me that self-awareness is any more valuable a skill evolutionarily for women than for men, just like intelligence isn't likely to be more valuable a skill for some ethnic groups over another. For example, generally speaking, and from an evolutionary perspective, analytical intelligence is no less an asset for a group performing less stereotypically intellectual activities (e.g. hunting) than for a group centered around stereotypically intellectual activities (e.g. accounting).
What do you think about the mis-alignment between goals here?
For medical research, the goal is to find general practices that will broadly help, and identify risks with the intervention. Even then, with many interventions, it's understood that they will effect people differently.
For individuals, they don't care about variation in communities, or standard medical practices, they are looking for relief for their specific condition.
Of course, declaring that just because something worked for one person, it should work for others, is wrong in both camps.
I feel like a big part of the disconnect here, and a big reason why people are talking past each other, is that they actually have different goals, and aren't really aware of that difference.
Well, to be honest I think the primary disconnect is in epistemological understanding. The OP did not declare peptides to be a personal revolution, he/she seemingly generalised their own experience to be widely applicable.
Basic human thought patterns usually lead people to think that anecdotes about their personal experience is valuable for understanding the world, but this is wrong. The scientific revolution basically illustrated the flaw in this premise outside of hypothesis generation. It takes specific education to make human beings truly believe that their anecdotal experiences are mostly irrelevant beyond understanding their immediate circumstances. The proportion of humanity that truly think this way is relatively small.
Understanding the world through anecdotes still works okay-ish for a lot of areas, but ascertaining relatively subjective effects of experimental pharmaceuticals is not one of them. But to many people it's non obvious that this is the case. And as a general method of thinking about this issue, it is just the wrong way to go about things.
And that's the disconnect, in my opinion. The OP drew a conclusion from a thought pattern that comes easily to human beings, but that is just wrong in this situation. Of course, perhaps this is reinforced by underlying motivations, but that's not what makes people talk past each other. These kinds of discussion are usually driven by so called "deep disagreements" in epistemological understanding, in my experience.
