stavarotti

> I’ve been running Kimi K3 alongside Claude on my normal coding work, and for all practical purposes I can’t tell them apart.

If the author is here, I'm curious what this means. How are they running Kimi K3? Are they using pi, opencode, claude, codex, or kimi-cli? Is speed a concern?

Without knowing how the comparisons are being made, it's hard to agree that one can't notice the difference. I do.

I’m curious, shouldn’t Mythos have discovered this? At this point, based on all the marketing from Anthropic, I’d expect all software from them to be flawless given all the capabilities Mythos possesses.

I'll be using it tonight but grudgingly so. Grudgingly because after July 7th, I'm not going to all of a sudden, start paying API prices (and maybe that's the problem) when I'm used to a subscription that gives me multiples in comparative value. Perhaps this is the fabled "token economics will come for everyone this year" that I've been reading about? In any case, I'll use the hell out of it to extract as much as I can, then back to the trusted partners Opus 4.6 and Sonnet 4.6 (for however long they remain available).

It’s the thousand cuts problem. Look at the stories over the past couple of weeks: silent downgrades that they then walked back, billing errors with claude code, highly sensitive classifiers that made it impossible to do simple things (I asked a few botany questions and my very long chat got lobotomized), and several more. The ban is only part of it. It’s the whole rollout and the fact that it won’t be available in subscriptions in a week or two.

I’ll continue to use the last great reasonably affordable duo from Anthropic: Opus 4.6 for planning and Sonnet 4.6 for implementation.

I just finished reading Incorruptible and a central theme (Anthropic is a case study) is that trust is singularly the most important currency a business has. The past few weeks have done wonders for Anthropic’s marketing but just as much if not more damage to the trust factor. Businesses will continue to use Anthropic because it’s the default and accessible where it matters (AWS, Azure, GCP, Databricks, Snowflake, etc). But the trust factor has dropped. It’ll be interesting to see if they can turn the tide. Maybe Fable will be too awesome for people to care about the past few weeks?

These style of comparisons are decent at showing capability but they don't really show me what I truly want - a sounding board and implementer with senior engineer-level execution. When I look back at all the teams that I've been part of, the best outcomes came from white-boarding (sometimes in the metaphorical sense) with one or two people, at times arguing, then finally compromising on a plan. Instead of synthetic benchmarks that try to be objective, I wonder if there's a way test this, or maybe I'm opining on a way of working that will soon be gone?

> On novel work:

> Work that introduces new methods, highly creative ideas, or solutions that have not been used or experienced before. More generally, an approach that introduces an innovative strategy to solve a complex problem.

Something that I've been thinking about for the past year or so is coming to grips with the fact that the vast majority (anecdote) of software engineering work is not novel (and maybe that's okay). Few opportunities lend themselves to doing truly novel work. Other than infrastructure work and highly specialized software, pause and ask yourself when you last encountered software were you said "how the hell did they do that?" or "damn, that's nice" (for me, the most recent was Ghostty). I think much of the angst that people have when they fear for their job is coming to the realization that LLMs can do most of the "standard" work that a lot of highly compensated individuals currently do. We've built livelihoods around this and the threat of that coming to an end is genuinely frightening.

The movie was great. I'm always fascinated by adaptations, especially what they choose to exclude. I thought the movie struck the right balance.

Such a fun game. It has the right amount of whimsy. Those shifty eyes…

We use Jira. We're trapped by the processes built around it. Once it's entrenched, it's rather difficult to remove. I eagerly await for something that can replace Jira, but fear that it too will be bastardized to fit the process for however long the process lives.

I'm curious whether this is due to their insistence on using home grown tools ie, Kiro and not Codex/Cursor/Claude et all? I tried Kiro and quickly left.

I've largely found codex and claude code to be about the same however, codex tends to "think" harder and for longer which depending on the task, yields better results without too much steering.

On an unrelated note, UI is such a personal preference that it's impossible, beyond core pillars that have been studied for decades, to say one is better over the other. That being said, I like OpenAI's design system much better than Anthropic. OpenAI products (cli and chat ui) "feel" nice and consumer focused whereas Anthropic's products feel utilitarian and "designed for business".