kimseungyong

It's a shame that it's not yet available outside the U.S. I'm using Dots; it's great that they keep me developing, but it still doesn't seem to be progressing well because it hasn't fully matched the quality I want or my context. (I may need to redesign the workflow with Dots) I want to try a Duet soon, too.

The day is approaching when Anthropic and Open AI will reign as the next generation of big tech. I guess it's an unavoidable cycle. Big tech companies, having grown too large, find it difficult to innovate quickly, and new generations emerge to become the new big tech players. What comes after AI?

Apple TV 4k, I really use the version of Apple TV 4k.I think it would be good to use a microphone It's so frustrating that price is so unhappy.

I wait for this open-source model.

I should let the development agent select a model and run it to improve token efficiency.

Is it being used this much these days?

I'm not sure which has more advantage compared to using only Claude Code.

I'm working with Claude's workflow, but I haven't yet felt any demand for customization.

For those who use this well, could you share examples of how you use it?

I just came up with an idea for a toy project: I would use dots to manage things like market research, checklists, and design ideas.

Since it starts with the Pro pricing plan, I’ll have to try it out later when it’s available on the Plus plan. Pro plan for toy project is too expensive.

I can feel that the token consumption has slowed down so that we’re able to cover more in a five-hour session than before. I'm using Korean, but sometimes the words or sentences are hard to read

Because the top-tier model is slow and expensive.

The models below are competing on value for money.

In service development coding, a top-level model is not required.

I hope this kind of competition continues.

When coding, the top-tier model is ultimately too expensive, so I use Opus, but the news that the cost per use for GPT or Claude is going down is very welcome. I really like that they’re even changing the writing style. I was worried whether it was a problem with my settings or if my literacy was declining. Both improvements are welcome.

I find it hard to agree that MCP merely wraps a simple API. Sometimes a filtered model-specific interface is needed. MCP is one of those interfaces. In our SaaS service, sensitive information can be viewed via REST, but since MCPs may be exposed to LLMs, they are blocked from going outside.

I've thought of ideas like this too

I still can't believe that an LLM can maintain all major service domains as documents

If too many documents are submitted, it will be hard to review, and if the domain is incorrectly set without me realizing it, the cost will be high when discovered later

AI operates on the device.

AI model vendors will likely be torn between developing their own hardware to avoid hardware dependency or moving forward together.

Quietly, Apple and Google will take advantage of this trend.

Anyway, AI operates on top of the device.

Among devices worldwide, who has the most control? Apple

They don’t build AI themselves, but when it comes to device infrastructure that allows AI to operate, Apple is naturally the strongest

Just as Meta had tried to build their own ecosystem through Libra and things like that

Won't AI companies end up doing the same? But that attempt doesn’t seem like it would be easy

Apple now feels like a kind of Coca-Cola stock

The problem is that, as seen in the case of the Houthi rebels developing missile software using Claude Code, AI has lowered the very threshold at which human cruelty or selfishness can be put into practice. Anthropic’s safeguards were applied on a per-request basis, but splitting the work into multiple sessions prevented me from seeing the bigger picture. After all, human instinct does not transform into technology, so the only remaining way is to pile up the friction that takes that instinct to turn into action all over again.

However, the international agreement proposed by Dario Amodei is ultimately nothing more than a promise made by people. There is also a precedent in which the Nuclear Non-Proliferation Treaty could have simply withdrawn if it had been cornered like North Korea. Isn’t the AI speed-control agreement also vulnerable to being broken in the same way if one side finds itself politically cornered. In particular, unlike nuclear weapons, AI has the characteristic of recursively improving itself, allowing its capabilities to accelerate itself, so the moment one side breaks away, the gap can widen in an instant, making the incentive for deviation even greater.