HN user
What does "scanning" mean though?
Does this mean every parent has to now make sure not to take pictures of their children playing in bath for instance, in order not to trip these scans for false positives?
For ages I've been looking for a way to easily share & sync a simple knowledgebase (HTML/MD and other files in folders) with my team (= including non-technical people), using Git as the sync/versioning layer, without it being too technical, and without getting vendor lock-in with expensive & unnecessarily complex cloud-based platforms.
Having built-in AI integration without relying on sketchy plugins would be the cherry on top (although, seriously missing the option to connect with any openai-compatible LLM provider like someone else mentioned here).
Seems like this might almost offer exactly that? I'll have to try it out...
I literally wrote how I measure this in the post you are replying to: #commits which is admittedly a worthless proxy for productivity, so, more importantly, number of finished production-ready features delivered.
That number is at least tenfold of what it was before, simply because I can run a lot of gruntwork in parallel now without wasting brainpower and focus on that stuff.
Seriously, what value are tokens providing other than justifying layoffs
Like the OP said, it's incredible how polarizing this debate is. When I read comments like yours, I feel like a significant part of the global workforce in IT must be living on another planet? Or they never really used Claude Code, Codex, OpenCode, ... intensively before because of company policies?
I legitimately am at least 10x more productive than a year ago, and I can prove it in number of commits and finished monetizable features developed per day. Obviously my workflows still very much require an active, constantly context-switching human-in-the-loop, but to me there's absolutely no question both output volume & quality have skyrocketed.
Isn't this just an artifact of their chain-of-thought reasoning? If they are verbose in their output, it's more likely the next word predicted is actually correct.
Also, I see this more as a feature than a bug. In many projects I inherited in the past, I wish the original devs were a bit more verbose. Then again, with every developer using LLMs now, probably the opposite applies now.
You could also use plain markdown files, any free Markdown editor/IDE, and git, and sync with a remote Git repo using gcrypt for encryption (git-remote-gcrypt).
It's just a bit of a pain to set up, and also, not mobile-friendly.
The 2% of cases when you need the commit log (or more importantly: someone else who inherits your code...) justifies writing good messages imho.
If you make a change to your codebase, normally you know what you want to achieve and why (otherwise... what are you even doing?). A commit message is just putting that in writing... that only takes a few seconds, often less than it takes to write the code.
So it's just a good habit to have. It forces you to think more about the changes you do & why, so it makes you a better software developer. Creating any new habit always takes some energy initially, but it's worth it.
Cool, but I wonder... is this really a feasible workflow?
The way I use LLMs is, I enter a very specific query, and then I check the output, meticulously reviewing both the visual output and the code before I proceed. Component by component, piece by piece.
Otherwise, if you just "let it rip", I find that errors compound, and what you get isn't reliable, isn't what you intended, increases technical debt, or is just straight up dangerous.
So how can you do this from a smartphone? Don't you need your editor, and a way to run your code to review it carefully, before you can provide further input to Claude Code? Basically, how can you iterate from a phone?
It definitely makes me lose interest and trust in software that is openly described as being "vibe-coded".
I'm with the vibe of wanting to move on to the point where LLMs are just yet another tool in the process of software engineering, and not the main focus.
I'm sure that would work out fine. Just like the GDPR regulation made the web so much better & more private, and the promise of the AI act is boosting innovation in Europe...
Exactly. So many local first libs don't cover this that it makes me wonder if the applications I am typically working on are so fundamentally different from what the local-first devs are normally building?
Most apps have user data that needs to be (partially or fully) shielded from other users. Yet, most local-first libs neglect to explain how to implement this with their libraries, or sometimes it's an obscure page or footnote somewhere in their docs, as if this is just an afterthought...
I'd highly recommend to add an "LLM Cheatsheet" page to your docs. Example: https://goatdb.dev/llm-cheatsheet/
No doubt this would help increase adoption these days, and make implementation a lot easier.
Radar-based device for measuring athlete sprint & agility tests.
A lot of professional sports clubs, S&C coaches, etc.. use timing gates for measuring sprints, but those are a pain to set up, only capture split times, and are expensive. I think radar (+ optional video overlay) provides a far superior solution.
There's this on the Bitcoin blockchain: https://opentimestamps.org
Meh, pretty basic. Most SaaS businesses have something like this in place already.
Closing inbound leads is relatively easy, since they've already shown active interest... The challenge I'm struggling with is (cold) lead generation: finding leads (and how to contact them) that match well with the service you're offering.
There are a lot of dubious scraping tools and B2B lead databases, but I feel like it should now be relatively easy to build a reliable web crawler & lead generator ... Does anyone know state of the art open source tools or services for this?
Probably yes, but his internal state doesn't matter, as long as the outcome is line with their original mission of open sourcing again :)
Why not? Someone changing their mind, showing repentance for past mistakes, and making corrective action ought to be a good thing.
Awesome! The name is just a bit funny if your native tongue is Dutch.
Honestly, it just highlights how little traction Bluesky has. We tried it within our company's niche, but it's like a desert. Feeds that rarely get updated. 0 engagement. What's the point? Whatever you may think of the management, X does the job (and arguably better than before). You can just filter out the stuff you'd rather not see on your feed.
Also, I second the other commenter's mention of the lack of sports on BlueSky. That's a pretty large category not to have...
I'd happily pay a fixed fee for a self-hostable desktop app version of this, that just uses Ollama/ChatGPT/Claude for the LLM part. Ideally open source too.
But yet another subscription? ... no thanks
You say you don't say anything about what we as a society should do about it, but it's definitely implied... or can be seen as such. Especially because it's quite a colored opinion - do you need a list of hoaxes and lies disseminated by the political left in the last 4 years?
Point is, everyone has biases, and everyone makes mistakes. We're only human. I think we should judge an information channel by the way they self-correct for those mistakes. That tells a lot about character and values, and whether or not to trust the source. So I believe we desperately need a meta layer on the Internet, much like X introduced with community notes, but on a larger scale. Open source, fully auditable, immutable (append-only and decentralized, so probably on a blockchain cause of the Byzantine Generals problem) - but I'll admit, that's just the tech geek in me trying to find a practical tech solution to a complex social problem.
I like monorepos as a developer, but as a founder, monorepos have one massive downside: if you want to hire outside help, you have to share everything.
While in some cases, the complete context is helpful for the job, in other cases, and I realize this may be pure paranoia but, you may not want to share the complete picture.
Problem is, the legacy media is confidently wrong about all kinds of matters too, all the time.
Why would they have the right to broadcast misinformation, and popular podcasters not?
The answer to this isn't censorship. It's in education and teaching people to think critically.
This is terrible. I was so happy CoffeeScript died a quiet death. Now someone thinks of this.
Keep it simple. Code should be easy to read. Also, ain't nobody got time to learn yet another obscure abstraction that will add only a marginal productivity gain at best (and probably sacrifice readability + add another build step + add another learning curve to new devs in the process).
Working mostly on https://www.ledsreact.com/ these days
We built a radar-based device for (gamified & fun) agility testing and training with accurate measurements, for top athletes. Works without wearables or expensive and complex/location-restricted setups like you have with timegates or LPS sytems.
If anyone here is into sports science & tech, feel free to get in touch! (laurens@ the domain above) We're looking for a sports scientist / product manager to strengthen the team, a marketeer with affinity for sportstech, resellers & partnerships, and of course, more customers :-)
I get frustrated when I join a project that doesn't allow running the full stack locally, but forces sharing parts, which always comes with limitations (not being able to work offline for starters).
It already is quite easy to spin up a local PG instance with Docker, but this probably makes it even simpler. Importing mock data and running migrations should just be 1 `npm run` command with a properly set up codebase.
RAG is all you need*. This is a pretty DIY setup, but I use a private instance of Dify for this. I have a private Git repository where I commit my "knowledge", a Git hook syncs the changes with the Dify knowledge API, and then I use the Dify API/chat for querying.
*it would probably be better to add a knowledge graph as an extra step, which first tells the system where to search. RAG by itself is pretty bad at summarizing and combining many different docs due to the limited LLM context sizes, and I find that many questions require this global overview. A knowledge graph or other form of index/meta-layer probably solves that.
I don't know why, but this program had difficulty opening what was clearly a correct SQLite3 database file (created with TypeORM) on Ubuntu 22.04. "Reason: Invalid file format". I ended up using Beekeeper Studio instead, which didn't have any problems with that file. I wonder if that bug is fixed.
I used remoteStorage.js for a while for an app, but the JS SDK was too limited. I'm surprised to see the last commit was just last week. Is it still maintained?
I never understood why it barely took off, the benefits of local-first are great and a competitive advantage to capture those privacy-sensitive users seeking to own their data. Hoping for a revival...
Does this also manage the infrastructure side of ETL? Usually some parts in a complex ETL process take a lot more processing power, so are run on different machines. From a quick glance at this, it seems like a WYSIWYG ETL tool for running ETL jobs on one machine?