Viewing profile — kakugawa

I feel like there's going to be a migration to a new interface paradigm that's balanced between agentic use and human review (with light editing). The current low/no code UIs are h…

They can at least deliver baseline value, because it's all text-based. Do agree that it'll become more complex, when/if they decide to create custom protocols.

The prefix cache is a resource shared by all users. This is basically a tragedy of the commons.

The more subtle point is that there's a gap between the task and its verification. e.g. if you have an open-ended / under-specified prompt, the verification needs to be able to han…

Antigravity CLI (which replaced Gemini CLI): https://antigravity.google/product/antigravity-cli

Here's the demo: https://docs.qwenlm.ai/resources/mlu56_demo.html Here's the description of the world model prompt for the web domain: "A precise GUI state simulator — given the cu…

How much does /goal actually help? In auto mode, I've tried using and not using /goal and I haven't felt a difference. https://code.claude.com/docs/en/goal#how-evaluation-works > /…

Are the "clicks around the UI" converted into end-to-end tests eventually? e.g. via playwright.

So, how is it being disabled? It still shows "Fable 5" on all surfaces (to me). Is it being silently degraded to Opus under-the-hood? Edit: Fable 5 was just disabled.

I didn't see Fable 5 in the `/model` list, until I ran it with: `$ claude --model fable-5`

a11y testing is non-trivial. axe-core can automatically detect many types of issues. However, enough compliance (to avoid being sued) needs end-to-end testing and human judgement. …

Thank you for pointing this out.

Opus 4.7 does not support disabling adaptive thinking (web, Claude Code). [1] Like the OP, I experienced similar issues and I'm glad that they brought back the ability to disable a…

It's prob why they chose a11y features. They have more pain, so they're willing to tolerate more growing pains. (And prob more motivated to provide feedback.)

I've found Google AI Search to be good for really topical searches. And its conversational ability has noticeably improved over the last year. I can now have a (short) conversation…

https://claude.ai/settings/general (Instructions for Claude) --- Treat my claims as hypotheses, not decisions. Before agreeing with a proposed change, state the strongest case agai…

He uses AI himself, so I agree he doesn't see AI use as black/white. Hard agree about ideas, thinking, advice. AI's sycophancy is a huge subtle problem. I've tried my best to creat…

You could view it as a specific application of the quote. In your quote, there is no time-dependency between the lie and the truth. Whereas here, it's an attractive lie (easily par…

Have we forgotten how bad LLMs were at citing sources when they first came out? So, we had to build a lot of structure (harness engineering) and frontier labs had to do specific tr…

gemini-cli has not been useable for weeks. The API endpoint it uses for subscription users is so heavily rate-limited that the CLI is non-functional. There are many reports of this…

In mid-2024, Anthropic made the deliberate decision to stop chasing benchmarks and focus on practical value. There was a lot of skepticism at the time, but it's proven to be a pres…

That's how you know you've made it: when your pet benchmark becomes a target.

How much longer is Anthropic going to allow OpenCode to use Pro/Max subscriptions? Yes, it's technically possible, but it's against Anthropic's ToS. [1] 1: https://blog.devgenius.i…

It's short-term vs long-term optimization. Short-term optimization is making the system effective right now. Long-term optimization is exploring ways to improve the system as a who…