HN user
Really interesting product. A ton of these sandbox companies recently but it feels like no one has really nailed the experience for application builders yet.
Really excited to try this one out
I’d also argue it needs to compile fast/ have fast static analysis. Feedback loops like this are super helpful for agents
disclosure: i run a startup that will most likely be competitive in the future.
I welcome more innovation in the code forge space but if you’re looking for an oss alternative just for tracking agent sessions with your commits you should checkout agentblame
Maintainer here.
In the case where a human edits a previously AI-generated line we simply track that as a human-produced line of code. We are thinking of making this a distinct subcategory because there's a lot of useful info in that data.
Regarding performance we haven't done rigorous benchmarks but we've been using this internally and haven't noticed any problems
Do you have examples of any of these ideas being implemented? In general I agree, there’s so much opportunity for these “knowledge augmented” algorithms
Curious how this scales. Just tried this with the test dataset and it was probably the slickest deduplication experience I’ve had
Is there any way to even use this today? I’ve been waiting for the server and file system components to be open sourced for a couple years now
This seems weirdly hostile. He laid out a bunch of points but you’re grabbing on to this one to make it seem like he’s using classic corporate-speak. Do you find it so unrealistic that the CEO of Sourcegraph has heard from devs that their managers asked them to try to clone or investigate the product before buying? That seems pretty likely
What was the breakthrough and what have we learned? I'm interested in reading more about this
This post is a bad analysis.
While some will praise Satya Nadella and hero-worship Sam Altman, breaking OpenAI into two parts will slow down momentum for LLMs and research while handing even more power to the Cloud and Azure in its future
Except that Microsoft nor Sam is responsible for the breaking of OpenAI. It was the non-profit board. Instead now Sam and co will have access to the Microsoft war chest, funding for more compute, chip design, and datasets so if anything they’ll probably move even faster than before.
Microsoft taking Sam Atman and his followers in, is like shutting down your best investment just for a short-term benefit. These stories don’t usually end well for big corporations.
Again this makes little sense and its very clearly obvious how this makes long term sense for Microsoft. Also they did not initiate this move by OAI
It’s the job of Venture Capitalist to praise Microsoft, Satya Nadella, and Sam Altman to vilify OpenAI’s board in all of this.
No it isn’t
Microsoft eating OpenAI and poaching their talent, is the worst possible scenario for the startup that was just beginning to get momentum.
No firing the beloved CEO of the fastest growing tech startup in a decade and ignoring warnings from 80% of employees that they would quit is the worst scenario for a startup regardless of what Microsoft does
This whole post seems like really bad pattern matching by someone who is anti capitalism and tries to frame every scenario they see in business through that lens
Can you be more specific about what was “solved” in the 90s? The platforms upon which apps are run now and the technologies as well as the expected capabilities of those apps have drastically changed. Not all UI development has changed just for being shiny.
I see little reason why building a UI today cannot be a superset of what was solved in the 90s so I’m curious to know what that solved subset looks like to you
I am negative for the Celiac blood test (got tested three times) but I am absolutely allergic to gluten. Starting three years ago randomly I became allergic and severely ill for months - losing up to 30 lbs in a matter of a month - before isolating the problem to gluten. I have also on multiple occasions accidentally eaten gluten without realizing and immediately felt the symptoms. None of the tests I've taken show gluten as an allergen or problem in my body but cutting it out removes all my symptoms. Our tests are not nearly good enough and I suspect many people deal with chronic inflammation and other health issues due to food they can't eat and don't even realize
Just a personal blog with some essays that I post occasionally to get myself in the habit of writing. My next post will be about living with chronic illness as a SWE and how to get through it
Companies have been gathering data for over a decade now and storing it in massive data warehouses with often no plan for how to effectively use it. I would not be surprised if turning those warehouses into a source for various LLM applications becomes the dominant use case for the industry very quickly. I expect we'll see some of the big incumbents like Snowflake roll out first-class vectorization of existing warehouses in the coming months.
Inflation has been remarkably low since 1980 though… and that graph doesn’t mention prices. Theoretically if more is being produced then you don’t need wages to keep up to afford the same luxuries. In fact all the stats I’ve seen shown that we can and do afford a lot more these days
Whenever I read articles like this I have a lot of sympathy and also a little confusion. Maybe it's because I DO have an adblocker but this just isn't my experience on the web. It feels so easy to use the web and generally avoid the deluge of shit OP talks about. I pretty much only go to sites on my bookmarks. I don't read the news (maybe that's a big part of this), I read blogs, forums, and then do some shopping. The rest is just work related stuff. The only time I'm ever really exposed to this sort of crap is Twitter but I curate who I follow and I try to stay on my chronological follower-only feed. Yet every time I see my parents using the internet it looks like an entirely different experience. It's unfortunate and sad
Entertainment: - Blindsight - Children of Dune - War and Peace
Curiosity/Knowledge: - Peter Zeihan (author) - Atomic Habits - Turn the Ship Around
Work: - Domain Modeling Made Functional by Scott Wlaschin - Designing Data Intensive Applications by Martin Kleppman
Don’t know why this is being downvoted when it’s objectively true. Parent says wealth inequality is less in Europe therefore being “poor” is more desirable which makes no sense. The US could have higher inequality but that could just mean the richest are richer and the poor have the same standard of living. It could mean the poor are poorer in the US and the richest are even. It could mean the poor AND the rich are richer and better off than their EU counterparts. Just looking at inequality numbers doesn’t tell you anything about quality of life between the two continents…
I actually completely agree with the author. I remember coming across my first unless statement while trying to find the source of a nasty bug and I spent probably 5 minutes just trying to decipher the behavior of the unless block because my brain had some roadblock with the double negatives. This has become a lot easier to understand as I’ve used Ruby more but it still seems like a massive opportunity for cognitive complexity and errors for little gain
This falls apart when you want to get married and have kids? It’s certainly possible to find a frugal partner but kids still cost a lot of money in general
Don't really know the situation too well but I really appreciate these explanations. I think what people often misunderstand about Bloom and other bootcamps is 1) education is really really hard in general and software engineering is a really hard topic. I'd argue the default is most won't succeed. 2) Bootcamps like this are fighting an uphill battle because of selection bias. If you're applying to a bootcamp like this it's probably because you couldn't get into a college or you did but dropped out or don't have the money, etc. People think it's bizarre when 30% of grads stop looking for a job but it makes sense. These are people from all walks of life with different constraints than the average student. 3) Regulatory schemes in general is batshit crazy in the US. Messing up here and there is not always indicative of malintent, especially for a startup.
This is certainly a problem domain that needs to be solved imo so I'm rooting for Bloom unless they really prove to be harmful. We need better pipelines for people with talent and motivation to climb the social ladder and learn new skills outside of traditional academia.
I can only assume you've never worked at a company even close to the scale of Amazon. There's no such things as "fixing it" with a lot of these internal tools. They'll often have entire teams dedicated just to developing these tools. More often than not you won't even have access to the source code and even if you did it would probably be incredibly difficult to make any meaningful changes.
You say it would literally be faster to stop feature work and fix the broken thing which is a laughably naive view on how these companies operate. That's just not an option unless you do it all on your own time in which case you will still be incredibly limited on what you can change and even if you make a significant fix there will be no extra reward for doing so. The incentives are all wrong.
A lot of comments here dismissing OP but I’ll say this. 1) it’s really not too late. You’re older than most that have kids but it’s really not impossible. You can have a surrogate or adopt or still try natural and screen for abnormalities. 2) I think it’s quite rude and destructive to dismiss someone who is obviously depressed because they regret an irreversible life choice they made by saying they need to find inner peace. By far one of the most crushing situations in life is the sheer reality that no matter what you do you cannot turn back the hand of time. Telling OP he nees to find inner peace and needs to learn about himself before he can even think of having kids isn’t very helpful. It sounds like he has learned about himself and it sounds like he realized he’s made a decision he deeply regrets and is faced by thag every day. Of course he won’t have inner peace why should he? I think in the long arc of a life yes he’ll need to readjust his internal narrative and come to terms with his life but if he’s depressed because he dodsn’t have children in his life I’m inclined to believe him and the logical conclusion is that having kids can help. It’s not too late and OP should explore all the options out there if he is serious about this.
Do you have a reference for that Netflix story?
I use image thumbnails for my blog posts as well but they don't even show up in the article. Instead when the article is linked to on twitter or a message the thumbnail will show up. That's to say that this is pretty awesome and very valuable for a blog even if not used for cringy pop-gif stuff in the article.
I really like EdgeDB so far. Only played around with it for side projects up to this point but with 2.0 and the introduction of Object Level Security I will definiteyl use it in production.
The EdgeQL is the first graph-based query language that is more intuitive to me than plain SQL and the local dev experience has been far smoother than pretty much any other db I’ve used to date. Really excited to see this project mature.
I live in East Village right on the border with the LES. There's certainly development happening and new buildings coming up but when I walk around EV/LES it sometimes feels like I see more 2-3 story buildings than otherwise. There's literally no reason any of these buildings should be under 6 stories minimum. People think of Manhattan as being dense with a bunch of skyscrapers but I suspect in reality there's still a whole lot of units that could be added by simply building upwards.
I say 6 stories because you can reasonably have a 6-story walkup. Anything higher and you would need to add an elevator which could make things harder.
I’d love to learn more about how you do this. Do you have any helpful resources that I can look at to understand the process of creating a DSL with TS + Pulumi?
Starting a new project and trying to decide between Go and F# of all things. Go seems fast and very widely used which means resources and help is widely available and it’ll be easier to find contributors. Meanwhile coming from the C# world at my job I really like the syntax of F# from what I’ve seen so far. The type system seems incredibly expressive in a way Go’s isn’t, access to C# libraries means I can do pretty much anything I’ll need to, and I enjoy FP paradigms even though I’m not looking for full FP (I generally like loops and escape hatches from FP if I need to do something specific). What’s your experience with F#? I’m worried about support and finding other people familiar with the language, not a huge fan of nuget, and I prefer to use VSCode but C# has been impossible to program in VSCode imo.