asnyder

You can set this up yourself with API keys to the corresponding providers and creating an Agent Group in https://github.com/lobehub/lobehub. Agent groups allow you to easily create a room of agents and have them discuss any of your topics. Easily make agents with types and skills, it even assists in drafting starting prompts and even team members depending what your query (and selected model) is.

You can self-host as well, but not via desktop app. Sever setup required.

Be careful of your token context, you can easily rack up costs if you leave Opus selected as the model and get lost in some rabbit hole of results.

Enjoy enjoy!

Nothing stops that from happening. Just needs to be trained in that DSL. Though at that point it returns to it's original form as a better autocomplete/IntelliSense :).

That will likely happen in the specialized fields. We can already see tools like Figma, Mira, and others that generate functional-ish frontend components in full typescript and corresponding styles (that are also selectable and configurable in the interface). Though, not quite as free, since they do load their base framework and components to ensure consistency and sanity / error-checking, etc., but even then it is in fact generating you useable, modifiable components that you can engage with in precision in your normal DSL.

For video, this likely exists, or is being worked on as we speak. All specialized domain tools will go towards this model to allow those domain experts to use the tools with the precision they expect AND the agentic gains we already take for granted.

I know the developer who worked on it took pride in the outcome. Hopefully they added some additional characters to keep it fresh.

Despite their confusion as to whether they want to really support their free and open source versions (without some absurd user count cliff), Mattermost (https://mattermost.com) is quite excellent and IMO is better than Slack. For example, editor leans towards native Markdown so things like syntax highlighting with backticks work as you expect.

Their recent update removed the paywall from SSO (and unfortunately the Gitlab SSO workaround) for social logins up to 100 seats, afterwards there's an absurd per seat cost similar to its non-open source brethren. One day if needed, I plan to drop-in an SSO middleman allowing anyone to leverage their own SSO layer (which will map to the login form with username/password) to avoid the SSO limits altogether. Though good enough for my needs, and likely yours too. Especially if you're open to paying for their seats.

Unfortunately there are many companies that actually rely on SMS confirmation codes in real-time, which include reading it back to them.

A legitimate and generally well liked company, and its real helpful service representative used this method to verify my identify before they could finish their support effort.

I've mistakenly given Chatbox a new feature, sorry :). In LobeChat, after you select a particular model, it enables a mini-settings menu next to the model that lets you set caching, deep thinking, and thinking token consumption.

I see Lobe and Chatbox both have prompt caching toggles, are you referring to something else?

How does this compare to the already established open source solutions such as Chatbox (https://github.com/chatboxai/chatbox), or Lobechat (https://github.com/lobehub/lobe-chat)?

Been using both, like Chatbox for how snappy it is, but is local only, vs Lobechat which allows you to setup centralized host to have shared host across clients but feels a bit clunkier.

Thanks so much for the update. Had no idea. Seems all the main channels moved over. Thanks!

#freenode was generally the main IRC node I used with all the good dev rooms.

Seems to still be chugging along. You can even join directly via their web-client: https://freenode.net.

Personally I still use pidgin.im to connect to all the relevant #freenode goodness. Seems people forget it still works and is pretty great even all these years later :).

Gift article: https://wapo.st/4od1but

Seems to be missing quite a bit of history. As many here mention, there was an entire ecosystem of tools to convert PSDs to HTML such as CSSHat, Engima64, etc., and its evolution into Avocode, Sketch, Zeplin, Invision Craft & Inspect, and other preview/prototyping/inspect/export tools.

Eventually all roads led to Figma somehow, which honestly I would've never expected. Still surprised Figma became Sketch before Sketch could become Figma.

There's also open-source solutions such as rocket.chat, Mattermost, and likely a few more I haven't played with.

I wish Mattermost wasn't always trying to nudge you out of community version, but otherwise pretty solid, better than Slack IMO. Is unfortunate they require weird gitlab spoof bypass to use SSO in community version. Shameful it's not out of the box.

Many years ago Pidgin with multi-channel IRC was all I needed, but seems Slack killed that whole party, which brings us to the current situation :(.

I know Liveblocks.io has been making this very easy and accessible over the last few years. They recently introduced AI, and are promoting that of course, but as I understand it multiplayer collaboration (https://liveblocks.io/multiplayer-editing) is their meat and potatoes.

Not affiliated with Liveblocks, just aware of its existence.

Opening up one's device does not void the warranty in the US. We have the Magnuson-Moss Warranty Act which forbids this, despite manufactures trying to groom us otherwise with those void if removed or broken stickers.

Most recently, FTC started to raise awareness and crack down on some abuse: https://www.ftc.gov/news-events/news/press-releases/2024/07/....

Will take a long time to de-program and by that time nothing will be replaceable to matter due to industries march towards preventing repair altogether.

There's also https://openobserve.ai, while not as stable as Grafana/Prometheus/Clickhouse, feels a bit easier to setup and manage. Though has a bit of ways to go, does the basics and more without issue.

Crazy crazy they spent so much on observability. Even with DataDog they could've optimized that spend. DataDog does lots of bad things with billing where by default, especially with on-demand instances you get charged significantly more than you should as they have (had?) pretty deficient counting towards instance hours and instances.

For example, rather than run the agent (which counts as an instance regardless of if it's on for a minute), you can send the logs, metrics, etc. directly to their ingestion endpoints and not have those instances counted towards their usage other than log and metric usage.

Maybe at that level they don't even get into actual by usage anymore, and they just negotiate arbitrary amounts for some absurd quota of use.

Nope, is completely the same base. Scroll the homepage, and you'll see an example of Livecode (updated HyperTalk).

You can open your HyperCard stacks, or MetaCard stacks, or Runtime/Livecode Stacks in their IDE, code, edit, etc, similar to what you would have back in Hypercard days, but with modern features, updates, and additions.

It's backwards compatible with HyperTalk, its current language is an updated HyperTalk (i.e. an updated MetaTalk), that incorporates all that was, but adds new features for today.

Your Livecode apps can be deployed and run as cross-platform desktop applications (Mac, Win, *nix) , mobile applications, and as far as I remember, web applications with HTML5 deployment (so they say).

Not affiliated with them in any way, just sharing my understanding and memories.

His legacy still exists and continues today. Even updated to modern sensibilities, cross-platform, and compatible with all your legacy Hypercard stacks!

As far as I remember, progression was Hypercard -> Metacard -> Runtime Revolution -> Livecode.

https://livecode.com

I was a kid when this progression first happened, my older brother Tuviah Snyder (now at Apple), was responsible for much of these updates and changes first at Metacard and then at its acquirer Runtime Revolution.

I even wrote some of my first programs as Hypercard compatible stacks. Was quite fun to see my apps on download.com, back in the day when that meant something :).

I always joked it required please and thank you due to its verbosity, but was super simple, accessible, and worked!

How nice, that even today one can take their legacy Hypercard Stacks and run them in the web, mobile, etc. Or create something new in what was more structured vibecoding before vibecoding :).

What about integrating Altcha (altcha.org) is hard? Seems pretty straightforward.

Seems there's either too much supply of drivers, and/or this whole cat/mouse gambling game, is overall adding waste and inefficiencies in the system. Seemingly by design to hold on to the driver pool while the drivers not realizing they're cogs being shelved in the system at the drivers own cost time and monetarily.

Pretty amazing how far behind regulation is compared to all these dynamic dark patterns. Not only in Uber, but in most everything we encounter these days, we're being guided, routed, or decided upon by unregulated dark patterns that would clearly be illegal if the details of which were exposed and explained in a way that anyone could understand.

Gift article: https://www.nytimes.com/2025/05/14/technology/lax-uber-drive...

Gift article: https://www.nytimes.com/2025/04/23/technology/trump-private-...

This sounds really really nice. Potentially exactly what I've been hoping would exist. Thank you for putting it out there!

Will try it out over the weekend. Exciting stuff.

That's always been the justification to skip this phase :). Tools have just changed. One-person to small-team wonders that could code and build directly made the same arguments.

My point isn't to stitch things to Figma, that's abhorrent to me as well. My point is to not get bogged down on the implementation details, in this case an actually working DB, those tables, etc, but rather less fidelity actual full flow concepts that can be generated and iterated.

Then that can be fed into a magic genie GPT that generates the front-end, back-end, and all that good jazz.

Every scientist does that at some point. I've easily crossed my fingers and hoped numerous times that code I'd written would work, especially on the first time. Even more rewarding in the superstition when the project is hard, and you're a bit daffy at the end.

It's a human thing.

Surely Feynman made jested comments before running experiments. I'm sure some digging in his wonderful books and letters will find many examples.

Back in the day we'd call this phase a design and workflow prototype as to not have to deal with all the technical components until the actual flow and concept is done.

Feels we're skipping these steps and "generating" prototypes that may or may not satisfy the need and moving forward with that code into final.

One of the huge benefits of things like Invision, Marvel, Avocode, Figma, etc. was to allow the idea and flow to truly get its legs and skip the days where devs would plop right into code and do 100s of iterations and updates in actual code. This was a huge gain in development and opened up roles for PMs and UI/UX, while keeping developer work more focused on the actual implementation.

Feels these generate design & code tools are regressing back to direct-Code prototypes without all that workflow and understanding of what should actually be happening BEFORE the code, and instead will return to the distractions of the "How", and its millions of iterations and updates, rather than "What".

Some of this was already unfortunately happening due to Figma's loss of focus on workflow and collaboration, but seems these AI generation tools have made many completely lose sight of what was nice about the improved workflow of planning, simply because we CAN now generate the things we think we want, doesn't mean we should, especially before we know what we actually want / need.

Maybe I'm just getting old, but that's my .02 :).

Gift article: https://www.nytimes.com/2025/03/20/world/europe/us-france-sc...

It's obvious isn't it?

Owning the Libs!!!

We have to separate his goals as a politician and his need for righteousness.

Trump gave him clear wins in his previous statements prior to the outburst. He committed to continued weaponry but emphasized he'd prefer the fighting to stop. He committed to NATO. He committed to getting back as much of the land, or more than you'd think, all clear progress from his previous statements and position in prior weeks.

Remember, the Mineral deal was already agreed upon. Trump, in my view, was being gracious and gave him additional wins. Had Zelensky taken those wins, NOT added an a whole unnecessary unprovoked debate with Vance, he would've ended that first meeting with those wins, EVEN with all that he said prior to the blow-up, some of which was already ungracious from Trump's perspective.

After the signing at the 2nd press conference he could've went into his whole need of security guarantees to protect their now mutual interests. He could've asked Trump to help him build "a big beautiful wall" to protect from the vicious x, y, and z, and still iterated, strongly to the press and world his needs, perspective, etc.

That's how a politician should've operated. Got there, carried out agreement which gives Trump face to his followers, taken the additional wins, and after all set, broadcast his views strongly and respectfully to the world, setting up a clear pathway to additional security in the future.

Win, win, win.

Instead he got none of that, and may even lose the current funding and support they were getting as Trump is still Trump and will likely want to extract some pain for his perceived slights.

Objectively, from a political perspective, we can see the outcome wasn't great, especially compared to the version of events that was being setup prior to the unnecessary confrontation.

Honestly, after watching the full press conference twice, I suspect this meeting will go down in history as a canonical example of "what not to do as a politician".

It seems Zelensky was unaware he's dealing with Trump, his demeanor, and his presidency. Historical this or that is not applicable when dealing with someone like him. Trump will be Trump, and nobody should expect otherwise. Always best to understand and know your counterpart.

I'm definitely no Trump supporter, but objectively, prior to the blow-up, Trump was being somewhat reasonable. Maybe the most Presidential I've seen him. He reaffirmed support for NATO, continuing sending weapons to Ukraine, and generally wanting to push efforts to stop fighting, etc. He respectfully let Zelensky speak numerous times, at length, on difficult subjects, even things he didn't agree with. He even respectfully looked at photos of prisoners offered by Zelensky. Compare that to his prior behavior with the UK Prime Minister just a day before where he cut him off numerous times forcefully.

Zelensky made numerous mistakes, emotionally reacting and replying to reporters questions when not directed towards him, adding on more grievance, and generally not being as a politician needs to be. He clearly showed why being emotionally responsive doesn't work in a debate, court, or other significant and crucial meetings.

The supposed Mineral agreement may just be a way for Trump to look like he got concessions or something in exchange to look strong to his supporters, especially compared to his favorite archrival Biden.

If Zelensky had goals/aims he wished to reach, he should've done his best to ensure the truth and his viewpoint comes through when is applicable to the question being asked, but not offered voluntarily or in conflict with his ally's statement. His demeanor from the beginning of the broadcast was already chilly and stern. He should've let any need for venting to come out AFTER the signing, at the 2nd joint press conference scheduled for later in the day.

If you watch Vance's initial statement, it was relatively supportive of Ukraine and leaned to neutral at the end. Nothing negative outright that needed to be added on to. Zelensky erred here by asking if he could ask Vance a question afterwards which led to the blow-up and escalation, and ultimately really bad decision of telling Trump he's going to feel this or that. This was a classic mistake. Question was over, should've moved on. Logically no possible statement could've helped his efforts or goals, so he only had the potential to hurt himself. Further being emotional, combative, and from Trump's perspective, relatively disrespectful did not help him. The entire over answering, and combative escalation was an emotional release from Zelensky and did not aid his aims, and ultimately hurt him.

He left in the worst possible position. He didn't get to his signing, nor his second opportunity for public statements post-signing, where he would've had clear gains, while forcefully stating whatever truths he feel were being left out or gaslit.

It seems Zelensky felt he needed to vent and express his people's pain, frustration, and anguish, but as the saying goes, time and place for everything, and unfortunately wasn't correct for either.