DIVx0

I've used argon via `agy` cli tool and was not impressed at all. However, I decided to burn up the remainder of my ultra credits on a visual reasoning pet project.

Argon in low and medium mode had higher quality results than it did when running in high mode, almost every time. My tasks involved the agent finding some details in a raster image and then mark it up with predictions about what it found.

Argon on high would do the work, and then a whole bunch of other stuff i did not ask for. All that extra broke everything else downstream from the analysis.

However, doing the same work with Argon in low effort was on par with results from Haiku 5.5 (xhigh) and GPT-6.1-Terra (medium). So, Argon low works better than Argon high, but for my tasks -- a very weak model relative to how google positions it.

I'm ready for Geimini Unobtanium!

Ngl, I got kinda excited by the submission title until the last two characters. Crediting LG as a development partner automatically sours the product, even before seeing details. Who has the time and money to beta test shit tier LG products while simultaneously fending off identity thieves or trying to RMA a broken device, as is tradition for USA bound LG engineered products?

FYI, it seems Modal will add $70 to your free "standard" accounts when you try out Endpoints.

I find when you give harsh feedback to claude it becomes "neurotic" and worthless, if "wtf" enters the chat, then you know it's time to restart or DIY.

oh I hope they really are paying attention. Even though I'm 100% aware that claude is a clanker, sometimes it just exhibits the most bizarre behavior that it triggers my lizard brain to react to it. That experience troubles me so much that I've mostly stopped using claude code. Claude won't even semi-reliably follow its own policies, sometimes even immediately after you confirm it knows about them.

claude code (CC) plan mode: In a normal CC window hit "shift-tab" until you see "plan mode on" in the lower left hand corner of the TUI.

Now all you really have to do is chat with claude about what you're thinking about building.

In plan mode, claude can't edit anything and has some extra "you're an expert at planning!" prompts prepended to your initial message in plan mode.

And then either when you're ready or Claude thinks the "plan" is gelling, it'll suggest stopping and let it write up a detailed plan. CC will dispatch some "planning agents" with prompts that your 'main' CC has crafted for that agent to plan for within the context of your conversation and what parts of the codebase it should look to integrate/explore.

Once all that is done, it will display it to you and then offer to "clear context and implement" - where it will just get to work. Or it will offer to go back to chatting and resolve whatever was misunderstood, or if you had a new idea you wanted to mix in.

These plans are saved as markdown in your .claude/plans directory.

Plan mode is handy on the on-off. But if you enter another plan mode, thinking claude would learn from, or build off a previous plan spec, it won't unless you explicitly say something like "read previous plan <path to plan file> and re-use the scaffolding directives for this new project"

I’ve tried GSD several times. I actually like the verbosity and it’s a simple chore for Claude to refresh project docs from GSD planning docs.

Like most spec driven development tools, GSD works well for greenfield or first few rounds of “compound engineering.” However, like all others, the project gets too big and GSD can’t manage to deliver working code reliably.

Agents working GSD plans will start leaving orphans all over, it won’t wire them up properly because verification stages use simple lexical tools to search code for implementation facts. I tried giving GSD some ast aware tools but good luck getting Claude to reliably use them.

Ultimately I put GSD back on the shelf and developed my own “property graph” based planner that is closer to Claude “plan mode” but the design SOT is structured properties and not markdown. My system will generate docs from the graph as user docs. Agents only get tasked as my “graph” closes nodes and re-sorts around invariants, then agents are tasked directly.

Agree with you, a slightly more maintainable way to use it now is with "uv" or mise. i've used `uv tool install unsloth` for this one.

Your employees are there to make your life easier? As their manager? Do you demand they make you coffee? Rub your feet?

I've been doing this for decades, and I've never seen that attitude work with any 'leader.' I'd hate to work for you. Ever hear of servant leadership? Or hear the line "My job is to clear the runway for you"

Managers are cost centers, 'your' employees are what keep you employed, give them the respect they deserve.

Glad that Norway has the immigration problem solved *eye roll*

Tell me more about how humans are criminals for existing? You hate the idea of someone standing on your piece of dirt without your express say-so that your preference is to live under an umbrella of fear and suspicion of your neighbors?

Forgive me, this is not how I want to live. I wonder how many Norwegians who settled in Minnesota were illegal immigrants?

can't sign up with gmail or "personal" email addresses? What if I want to evaluate but I am not ready to inundated with sales calls? My 'work' email domain is one that many vendors would love to see in their CRM. I always sign up with disposables first.

I guess I should thank you for saving my time? Plenty of others in this space.

I keep a similar kit of tools. However I still had problems fitting _everything_ i typically need in a small case. Typically I'd have to decide if I needed more socket or driver options and add/remove tools to accommodate.

I have since solved this problem: 1) Tool-Check PLUS from Wera: fantastic and highly condensed set of sockets, bits, ratchet and driver. all high quality. 2) Leatherman ARC: replaced a more basic multi-tool. I like the high quality blade material and the whole thing is very durable, i can squeeze and crank the pliers without worry.

The leatherman is a bit of a splurge but I highly recommend the tool-check for tool-using EDC minded folks. They make good gifts too.

I regularly play UHD HDR content I ripped from my blu-ray collection to my 4k AppleTV over 1Gbs Ethernet. I use the Infuse app instead of Plex, no stutters, no issues, looks great!

sidebar: I've had a lot of problems with the AppleTV plex app, it does not play some HDR content well, or at all. Plex on my nVidia Shield works well.

I really like Ilograph, I just wish the editor experience was better. It is hard to manage very complex systems with many perspectives.