Im so confused by this. Watching the demos it seems like they just do some OCR to fill in a form? Then grab an email and linkedin url? The demo takes ~10s to do that.
I was just looking through the Go example as well. For a first attempt its ok. I don't think its accurate to criticize that it doesn't make a case for using Go or teaching how to use it. It's attempting to be a more useful contributing.md. I think it does a decent job at that. Enough that you could find an area of interest and feel confident to start reading and understanding it yourself.
It just doesn't seem to be worth the effort though. I see myself using something like this for ~30 minutes to so I don't feel lost when getting started. After that it becomes significantly less useful.
Also, the video wasn't particularly helpful and if I have to here an AI voice say how fantastic something is again, Im going to unplug it (jk future overlords).
Orgmode has been on the back of my mind forever. Ive been working on implementing a system recently. My hesitation with orgmode is that I'd like to share calendar/todo list with my non technically minded spouse and I like Vim. Any suggestions?
There is org-caldav that you can point to an org file and it syncs with a caldav server. This way you can have two-way sync from e.g. a phone's calendar to your org file.
I'm in the exact same boat. I've started exploring https://github.com/nvim-orgmode/orgmode and it seems to be a pretty accurate emulation of Emacs Orgmode, or at least I haven't run into its limitations yet since I'm just starting to explore it. I still haven't solved the sharing of calender/todo info but this page has some ideas that could work to varying degrees: https://orgmode.org/worg/org-tutorials/org-google-sync.html
> seems to be a pretty accurate emulation of Emacs Orgmode
Oh, so it allows you to have source blocks in different languages where you can pass data between one another? I am highly skeptical it's possible in that fork at all.
I have not implemented a solution to this, but it's been on my radar for a while. The two best options of which I'm aware are:
1. Export a .ics file based on your agenda (support for this is built-in) to a shared folder to which your spouse has access (syncthing/dropbox/whatever). Your spouse would then use their calendar app to subscribe to the ics file. When you push changes to the ics file, they would automatically propagate on the calendar.
2. Use built-in org html export features to generate a simple page showing your schedule and either host it on your local network or put it in a shared directory as described above.
edit: sibling comment has a better suggestion (org-caldav)
I basically just wrote my answers in a neighboring comment, but I would try Spacemacs (default is Evil mode aka vim mode) backed with an Obsidian vault. I share a subfolder of the vault with my wife via iCloud, who can open it up on her phone and see the content and make edits in a non-techie way.
Whats your workflow? Ive been playing with Claude Code for personal use. Usually new projects for experimentation. We have Copilot licenses through work so I've been playing around with VS Code agent mode for the last week. Usually using 3.5, 3.7 Sonnet or 04-mini. This is in a large Go project. Its been abysmal at everything other than tests. I've been trying to figure out if I'm just using the tooling wrong but I feel like I've tried all the "best practices" currently. Contexts, switching models for planning and coding, rules, better prompting. Nothings worked so far.
Switch to using Sonnet 4 (it's available in VS Code Insiders for me at least). I'm not 100% sure but a Github org admin and/or you might need to enable this model in the Github web interface.
Write good base instructions for your agent[0][1] and keep them up to date. Have your agent help you write and critique it.
Start tasks by planning with your agent (e.g. "do not write any code."), and have your agent propose 2-3 ways to implement what you want. Jumping straight into something with a big prompt is hit or miss, especially with increased task complexity. Planning also gives your agent a chance to read and understand the context/files/code involved.
Apologies if I'm giving you info you're already aware of.
This is exactly what I was looking for. Thanks! Im trying to give these tools a fair shot before I judge them. Ive had success with detailed prompts and letting the agent jump straight in when working on small/new projects. Ill give more planning prompts a shot.
Do you change models between planning and implementation? I've seen that recommended but it's been hard to judge if that's made a difference.
Sometimes I do planning in stronger models like Gemini 2.5 Pro (started giving o3 a shot at this the past couple days) with all the relevant files in context, but often times I default to Sonnet 4 for everything.
A common pattern is to have the agent write down plans into markdown files (which you can also iterate on) when you get beyond a certain task size. This helps with more complex tasks. For large plans, individual implementation-phase-specific markdown files.
Maybe these projects can provide some assistance and/or inspiration:
I really don't get it. I've tested some agents and they can generate boilerplate. It looks quite impressive if you look at the logs, actually seems like an autonomous intelligent agent.
But I can run commands on my local linux box that generate boilerplate in seconds. Why do I need to subscribe to access gpu farms for that? Then the agent gets stuck at some simple bug and goes back and forth saying "yes, I figured out and solved it now" and it keeps changing between two broken states.
The rabid prose, the Fly.io post deriding detractors... To me it seems same hype as usual. Lots of words about it, the first few steps look super impressive, then it gets stuck banging against a wall. If almost all that is said is prognostication and preaching, and we haven't seen teams and organizations racing ahead on top of this new engine of growth... maybe it can't actually carry loads outside of the demo track?
It can be useful. Does it merit 100 billion dollar outlays and datacenter-cum-nuclear-powerplant projects? I hardly think so.
What commands/progs on your local Linux box? Would love to be able to quantify how inaccurate the LLMs are compared to what people already use for their boilerplate stuff.
I've found the agents incredibly hit and miss. Mostly miss. The likes of Claude Code occasionally does something surprising and it actually works (usually there's a public example it's copied wholly when you research the code it gave you, especially for niche stuff), but then the rest of the time you spend hours wrestling it into submission over something you could do in minutes, all whilst it haemorrhages context sporadically. Even tried adding an additional vector database to the likes of Claude Code to try and get around this, but it's honestly a waste of time in my experiences.
Is it "useless"? For me, yes, probably. I can't find any valid use for an LLM so far in terms of creating new things. What's already been done before? Sure. But why an LLM in that case?
The strangest thing I've seen so far is Claude Code wanting a plugin to copy values from a metadata column in WordPress to then read, which is triggered by a watcher every five minutes—instead of just reading the value when relevant. It could not be wrangled into behaving over this and I gave up.
Took me 2 minutes to do the whole thing by hand, and it worked first try (of course—it's PHP—not complicated compared to Verilog and DSP, at which it is spectacularly bad in its output).
It does very odd things in terms of secrets and Cloudflare Workers too.
The solutions it gives are frequently nonsensical, incomplete, mixes syntax from various languages (which sometimes it catches itself on before giving you the artifact), and almost always wholly in how inefficient the pointless steps to a simple task are.
Giving Claude Code tutorials, docs, and repos of code is usually a shitshow too. I asked their customer support for a refund weeks ago and have heard nothing. All hype and no substance.
I can see how someone without much dev experience might be impressed by its output, especially if they're only asking it to do incredibly simplistic stuff, for which there's plenty of examples and public discourse on troubleshooting bad code, but once you get into wanting to do new things, I just don't see how anyone could think this is ever going to be viable.
I mucked around with autonomous infrastructure via Claude Code too, and just found that it did absolutely bizarre things that made no sense in terms of managing containers relative to logs, suggesting configurations et al. Better off with dumb scripts with your env vars, secrets et al.
make sure it writes a requirements and design doc for the change its gonna make, and review those. and, ask it to ask you questions about where there's ambiguity, and to record those responses.
when it has a work plan, track the workplan as a checklist that it fills out as it works.
you can also atart your conversations by asking it to summarize the code base
My experiments with copilot and Claude desktop via mcp on the same codebase suggest that copilot is trimming the context much more than desktop. Using the same model the outputs are just less informed.
I'd say for me, it depends on the task and the language. I find asking ChatGPT to generate some code that I copy and paste lines up with your experience. Same with using an agent in a new project. I find the error rate much higher though once I start asking it to write code using specific libraries. Or when using an agent in an established code base. It's also terrible with DSLs that probably don't have as much training data. Trying to get it to do anything with Azures KQL is borderline pointless.
Im fairly new to self hosting. I've been playing around with a raspberry pi running raspberry pi os. The documentation says the Debian package is only for amd64 architectures. Im assuming that has to do with one of the Node packages? Out of curiosity, if I wanted to get it to work on an arm architecture, where would I start? My first guess would be trying to install it on the pi and looking at the error messages.
I think the docker container has both amd64 and arm64 versions, so try following the docker-compose instructions.
Personally, I have a Services folder with sub-folders for each self-hosted service. Each service folder has a compose.yaml file, and any additional files that the service might generate also go into its service folder (e.g. /Services/audiobookshelf/ has config/ and metadata/ as well as compose.yaml). I don't need every service running constantly, so I just update and run things manually as needed, but you could automate that. I really appreciate that you can just use `docker-compose pull` to update and `docker-compose up -d` to run the service without having to mess around with anything else.
How did you learn to build a BitTorrent client? I love the idea of codecrafters and books that walk you through building something but I always struggle if I don't have something to get me started.
My starting point was searching for tutorials and asking ChatGPT to implement a torrent parser :) There are great blog posts [0] for building a BitTorrent client. Along the way, I referenced open-source implementations and the BitTorrent Protocol Specification as well [1].
reply