dimitri-vs

https://en.wikipedia.org/wiki/1337x

Anthropic: were commiting to being ad free.

Also Anthropic: if you use our models in any way that might negatively impact our revenue we'll sabotage you.

Can I pick the ads please?

Maybe not exactly the kind of tutorial you're looking for but very enjoyable none the less: https://youtu.be/eekCQQYwlgA

This is my exact vibesperience

Woah hold on there, having cameras in their office could be a huge violation of privacy!

I don't think it's as one sided as you think. I made a skill that has been exceptional at using Claude to handling support and getting me refunds with minimal friction on my end. It's got many pathways for escalation if customer support is unresponsive: social, TrustPilot, etc.

Take a look at Outline! I use it almost exactly like a cloud based Obsidian vault. And they have been very responsive for MCP feature requests

Almost certainly some kind of scam

Considering the amount of fungicide/pesticide needed even (especially?) for organic fruit, it would be suboptimal.

It's kind of like having a 16 gallon gas tank in your car versus a 4 gallon tank. You don't need the bigger one the majority of the time, but the range anxiety that comes with the smaller one and annoyance when you DO need it is very real.

The big change here is:

Standard pricing now applies across the full 1M window for both models, with no long-context premium. Media limits expand to 600 images or PDF pages.

For Claude Code users this is huge - assuming coherence remains strong past 200k tok.

The problem is it's not limited to code. I have Claude Code maintaining my Obsidian Vault, managing my Home Assistant setup via SSH, helping me buy life insurance and file my taxes and and manage my home orchard and...

I think they already are. When I used the prompt with 5.2 it gives very concise and general info but if you use older models (5.1 instant or o3) you get a ton of detail.

I've tried a bunch of them only to settle on using Claude Code with remote control.

As others have said: accountability

What's your budget? https://en.tokyodevices.com/items/128

But seriously you can probably DIY something a lot cheaper.

It's for people that don't know how or don't want to be bothered with setting up a messenger integration and a scheduler.

How would it know you've ran out of milk?

IMO Copilot was "we need to give these people rope, but not enough for them to hang themselves". A non technical person with no patience and access to a real AI agent inside a business is a bull in a china shop. Copilot Cowork is the closest thing we have to what Copilot should have been and is only possible now because models finally got good enough to be less supervised.

FWIW Gemini inside Google apps is just as bad.

I don't think LLMs are very good at introspection on what they know or don't know, but otherwise this is gold. Thanks for sharing.

API Opus 4.6 will tell you it's still 2025, admit it's wrong then revert back to being convinced it's 2025 as it nears it's context limit.

I'll go so far as to say LLM agents are AGI-lite but saying we "just need the orchestration layer" is like saying ok we have a couple neurons, now we just need the rest of the human.

Manual orchestration is a brittle crutch IMO - you don't get to the moon by using longer and longer ladders. A powerful model in theory should be able to self orchestrate with basic tools and environment. The thing is that it also might be as expensive as a human to run - from a tokens AND liability perspective.

I really don't see why AGI can't be a spectrum and we just have very weak AGI and going from weak to strong will take many years, if it ever happens.

And yet another way to look at it is maybe current LLM agents are AGI, but it turns out that AGI in this form is actually not that useful because of its many limitations and solving those limitations will be a slow and gradual process.

IMO if you haven't seen an agent (SOTA) veer off a plan and head towards a landmine you haven't used them long enough. And now with Ralph loops, etc it will just bury it. ClawdBot/MoltBot/OpenClaw is what ~2 months old so "hasn't happened yet" is a bit early to call.

That said, if model performance/accuracy continues to improve exponentially you will be right.

emailed a hallucinated suicide note to all my coworkers and then formatted my drives problem ... most people are willing to accept

Are they though? I mean, I'm running all my agents in -yolo mode but I would never trust it to remain on track for more than one session. There's no real solution to agent memory (yet) so it's incredibly lossy, and so are fast/cheap sub agents and so are agents near their context limits. It's easy to see how "clean up my desktop" ends with a sub-subagent at its context limit deciding to format your hard drive.

Maybe I'm just not working on complex or big enough projects but I haven't encountered a case of a feature that couldn't be implemented in one or two context windows. Or using vanilla Claude Code a multi-phase plan doc with a couple of sub agents and a final verification pass with Codex.

I guess maybe I'm doing the orchestration manually, but I always find there's tons of decisions that need to be made in the middle of large plan implementations.

Your refactor example terrifies me because the best part of a refactor is cleaning out all the bandaid workarounds and obsolete business logic you didn't even know existed. Can't see how an agent swarm would be able to figure that out unless you provide a giga-spec file containing all current business knowledge. And if you don't spec it the agents will just eagerly bake these inefficiencies and problems into your migrated app.

Exactly. If a user wants a simpler experience there is now the Claude Cowork option.

On the other hand the average human has a context window of 2.5 petabytes that's streaming inference 24/7 while consuming the energy equivalent of a couple sandwiches per day. Oh and can actually remember things.

It's simple: you just offload the validation and security testing to the end user.