zackham

Like others here I created my own terminal multiplexer as well. Daemon that holds all sessions, seamless binary upgrades so those sessions never get lost, everything recorded so recovery is always possible, thin client mode so laptop has a native app that connects to daemon, and a wasm responsive webui with transcription so I can carry on with sessions from phone. Claude/codex sessions started with a uuid so they can be killed/resumed at will (mine autosleep after 12h inactivity to free resouces). CLI allows agent control of everything for a harness independent implementation of claude's channels. A few friends have forked and adopted it as their daily driver. Similar organization to herdr wrt spaces to organize sessions. Optimized for speed/bandwidth when running in thin client mode.

https://github.com/zackham/seance

single author, single user software is the one place where there is no rev limiter on ai. i spend the vast majority of my time on the computer steeped in my personal software now. some i publish for others to use, or so friends can point their agent at to adapt/rebuild:

https://stepwise.run/ Portable workflow orchestration for agents and humans

https://github.com/zackham/aloop Embeddable Python agent loop for integrating LLM agents into your projects. Multi-provider (OpenRouter, OpenAI, Anthropic, Google, Groq), built-in tools, hooks, ACP server, and persistent sessions.

https://github.com/zackham/plat An embeddable infinite canvas to build on. Bring your own node types; drag, zoom, edges, auto-layout, and undo come free. Host-agnostic storage, runtime API built for agents.

https://github.com/zackham/seance Shared live workspace for humans and agents — multi-pane terminals, notes, and a control plane for co-working in the open.

deep dive docs for my personal agent system i've been developing since dec, and using constantly: https://vita-docs.ham.xyz/overview/

browser replacement for stuff i control: https://vita-reports.ham.xyz/s/2119130b0b6b

a snapshot in time of the education system i run for my kids: https://vita-reports.ham.xyz/s/e7036ae931a7

if you want to talk about any of this stuff, or have a related project you think i'd appreciate, hit me up [email protected] or @zackham on telegram. abundance is here for personal software. take advantage of it and have fun!

all ingested data and all derivations of that data can link to source channel and associated ACL that syncs with the source. then search/reads/etc just join on and respect the ACL. not that complicated to manage for things like slack, meetings, etc.

agreed. i built this for a wide variety of background workflows that have been running seamlessly for many weeks now. it's an overbuilt personal project but i think pretty dialed in and very flexible https://stepwise.run/

I have a project in this space that I've run many thousands of jobs through. It's solid and full featured. Feel free to connect: https://stepwise.run/

if you are looking for a customizable agent harness that provides everything except a tui (cli, acp, embeddable python package) i built and use this for a handful of projects where i needed a vendor-agnostic replacement for claude agent sdk: https://github.com/zackham/aloop

The most durable way to reason about agents is to just think about humans. We have thousands of years of prior art on coordinating instantiations of stochastic intelligence. Context, tools, goals, validation, specialization, distribution of labor, coordination... If jobs are bundles of tasks and areas of accountability, maybe it's more effective right now to unbundle and reorganize some of these things. If constraints underperform autonomy, maybe you have to adjust where you operate on that spectrum, and account for it in goal definition and validation. These are not new problems.

When I come across a paper/article/insight that connects to one or more things I'm working on, I generate 20-30 minute podcasts that do deep research, connect it back to my work, and target an angle I'm interested in. I can message my agent over Telegram and say "check this out [link] curious who else is working on this problem and if there's anything actionable we can glean from it in relation to [projectX], generate a podcast". It's been surprisingly good, and in my commutes I've found these more compelling to listen to than my normal rotation of stuff.

Here's an earlier version of my podcast generation flow before I built narrate: https://stepwise.run/flows/podcast-deep

agreed. the long-running tasks i handle with immediate-background and continually edit message with updates, along with fork-and-reconcile semantics so you don't have to queue messages. also having a supergroup with separate topics for different sessions works really well.

the separate topics approach along with allowing other processes to enqueue messages into the session stream solves state pretty tidily, see "the session as decision-maker" in the linked report

pi is great and made popular some things that are really valuable, that hopefully spread to more projects (arbitrary forking with /tree, system prompt transparency and control). i was hoping to use it on a few projects but needed something to embed, and it didn't quite fit the bill. ended up building https://github.com/zackham/aloop which i am using in coordination with https://stepwise.run/ - reach if you're interested, both under active dev and deployed in systems doing real work.

Hey - OP here. I've been working on Ride with GPS since 2006 (!) and the game we've built is the most fun I've had in a long time. We're launching in PDX and if that is a success, we'll double down on it and roll it out to a bunch more cities. I want to do everything I can to stack the deck in our favor since I believe in this project.

I put together this landing page start to finish yesterday (thanks claude/grok), and am hoping it's effective in generating some initial interest. Looking for any feedback you have, small/large, however blunt, to dial it in and make it work for us.

Ride with GPS | Full Time Remote | https://ridewithgps.com/about

We are the world's best library of bike routes, and we enable cyclists to go on better rides, more often. We have a website and mobile apps that allow people to discover the best riding in their area, and get turn by turn navigation using either our mobile apps or the bike computer of their choosing. Come join us in taking Ride with GPS to the next level!

Senior Software Engineer - iOS Development: We have a technically interesting, battery efficient app that offers a full-featured bike computer (ride recording, & route navigation), a route planning tool, as well as ride management, analysis, and more. We're looking for a talented iOS engineer to help us take what we've done to the next level.

Details, and application process available here: https://ridewithgps.com/careers/job_postings/2025-ios-engine...

I'll add to the sibling comment and say I've been writing software for money for 25+ years, have a CS degree, and have found immense leverage with these tools. I put in the time on hobby projects over the past couple years to figure out how best to integrate it all into my work, and now I'm in a place where it's saving me significant amounts of time every time I produce code, and I'm getting the quality of results the project demands. I use gemini-2.5-pro, claude-4-sonnet, and o3 for different purposes, and have a variety of techniques to avoid pitfalls and get the results I'm looking for. There are a lot of ways to unsatisfactory results, but it's possible to get usable results that save time. I've shared my enthusiasm and seen other devs dabble, get poor results, and go back to their practiced methods of writing software–so I'm not surprised to see so many skeptics and naysayers. It isn't easy or obvious how to make this stuff work for you in larger codebases and for meatier problems. That doesn't mean it's impossible, and it doesn't mean it's not worth it to climb the learning curve. As the models and tools get better, it's getting a lot easier, so I suspect we'll see the number of people denying the utility of LLM-generated code to shrink. Personally, I'd rather be reaping the benefits as early as possible, because I can get more stuff done faster and more pleasantly.

If you're using org-mode and thinking about customizing it a bit more, and/or would like it to serve you in a way that is a bit more aligned with GTD, this reference from Bernt Hansen is without peer and just an incredible contribution: https://doc.norang.ca/org-mode.html

I've used or built more personal knowledge/task/project management tools than I care to list over the years, and adopted various methods along the way. I've ended up in a place where I know what I need day to day: A place to dump my ideas, plans, reflections, and tasks, along with methods of processing and accessing all this data. It's hard to compete with plain text files, a notebook, and structured daily/weekly rituals that process these notes into actionable tasks, meeting agendas, and project docs. It's not that time consuming, it's super effective, and most importantly, it's infinitely and freely customizable because instead of software, you just have checklists and processes to manually follow. You can execute GTD without touching a computer: https://gettingthingsdone.com/wp-content/uploads/2014/10/Wee...

I can get by just fine with that system, but a handful of months back I started wanting software again. Reminders, task wrangling, workflows around taking meeting notes, taking and processing transcripts of talking through ideas, automated daily and weekly checkins with summaries, project work logs, managing lists of things to talk about with people, the list goes on....

Same reasons I have always reached for software, and the same reasons I wrote my own system a few times over. But this time I had some new thoughts:

- I want this to have a chance at being my last system. For that, I must be able to read/edit the data without special software. I settled on committing to building software that interfaces with folders of Markdown files exclusively. I could use Obsidian to cover any gaps and get work done immediately–I don't need my software to do it all right away.

- I want to own as much of my recorded activity/thoughts as possible, so I can drop it into new AI models, giving them a ton of context about me and what I'm up to, and avoid getting vendor locked to OpenAI.

- I want ubiquitous access to the system, which means it's gotta be easily used from a phone.

7k LOC later and I've got a Telegram bot with a plugin architecture and a pile of plugins that implement everything I've described and more. The plugin arch means there's a defined interface and every new piece of functionality never ends up with more than 1k LOC in a file. My objective was to structure the project specifically so I could avoid the pitfalls of AI generated code as projects get large. Everything isolated with well defined integration points.

I chose Telegram because they have a great API, supporting custom keyboards for quick actions, audio input for taking voice memos that my system transcribes, and reaching out to me with reminders/requests on whatever device I'm on.

The result is thousands of messages that have translated into a nicely organized Obsidian vault. Couldn't be happier and think there's a chance I'll live with this thing for the foreseeable future–and I can always swap out the interface away from Telegram, build a proper frontend, or drop it altogether and be left with my Markdown files.

If anyone is interested I'd be happy to share what I've got. Just my private project that I'm reaping a lot of benefit from.

Here's a quick dump of some of my plugin commands to get a flavor of what I'm talking about: https://gist.github.com/zackham/3c2d061e6dd0127958c913329aa0...

Ray Kurzweil has laid out a view on the future that has always been interesting and is feeling increasingly relevant. Incredibly, his prediction for AGI in 2029 seems... conservative? It's too bad this article refers to him as a "former Google engineer" and only bothers to cite a Youtuber talking about his books. He's a fascinating character, has been a prescient futurist for many decades, and his books are very readable - check them out! His big 3 are The Age of Intelligent Machines, The Age of Spiritual Machines, and The Singularity is Near. The last one is the most recent and popular, and is what I'd point people towards.

Ride with GPS | Web Frontend | Portland, OR | Remote

More details here: https://ridewithgps.com/careers

We're a small but very strong team (28 of us) helping people have a better time on their bikes. Specializing in route planning & ride recording (with an established website and popular app), we work closely with individual riders, clubs, events, tour companies, and more. Currently looking for a strong dev for Frontend Web (mostly React).

We work reasonable hours, have great benefits, love solving problems for our customers, go on bike rides and encourage each other to live healthy happy lives. It's a really nice working environment with a cool product and customer.

Please inquire for more info: [email protected]

I understand the points being made, it's just not what I choose to focus on in the very limited time I'm going to spend engaging with this material. The purpose of my comment was to let any other tech-focused visitors to this site know that I did find some value on the periphery of this book, in case they are equally uninterested in hearing everyone's hot takes on a 98 year old who's already had books written about his life's negative impacts.

I heard Schmidt on a couple podcasts[1][2] recently promoting this book, and I found them to be useful for understanding how AI is being discussed among the political and leadership class. I was surprised to see all the negativity here - I thought he made some interesting points, and I appreciated getting some insight into how decision-makers are thinking about this in terms of regulation and geopolitical risks.

[1] https://tim.blog/2021/10/25/eric-schmidt-ai/

[2] https://hiddenforces.io/podcasts/eric-schmidt-ai-human-futur...

This looks like a herculean effort over just the past few months. Congratulations on hitting this milestone and hopefully you can take a breather and tie up loose ends at a more comfortable pace. As much as HN has changed over the years I still think this is a place where there are a lot of people who can appreciate how you feel right now. Nicely done!

If your concern is that this is additional unneeded syntax that is just going to result in difficult to understand, overly terse code, my 2 cents is that a conversation among your team to discuss these cases and agree on some standards is a pretty straightforward solution. It's not like today's JS has the Python philosophy of "one obvious way to do it".

I'll throw my hat in with those on the sidelines excited for the language we're stuck writing more of than we may want to, getting another piece of syntax that improves the ergonomics in a lot of little cases. Much like destructuring, much like the optional chaining and null coalescing. It will be nice to avoid the occasional temp variable that isn't useful for readability, or to rearrange expressions that read better applied than composed... but mostly I'm looking forward to how much nicer a pipe operator makes iteratively doing something in the console.