agrippanux

I'm a big fan of Cloudflare products. I recently stuck Jev in front of a Cloudflare-hosted Ollama model for chat/username moderation, so I was excited to test out Clef. The setup is user send a message -> Jev does first pass to see if it's toxic/hate speech/profane, if Jev is unsure then Ollama on Workers AI takes a deeper look.

Clef was 2-3x slower and worse (it caught less hate speech) than Jev. Overall disappointing.

The change to how iOS lets you select cards in Apple Pay is worth the upgrade alone. Now you just swipe to select the card you want instead of having to tap through multiple buttons/modals.

Fable orchestrating DeepSeek v4 Flash to implement a plan is my new favorite thing.

It's so freaking fast, but you gotta tell Fable to watch Deepseek like a hawk or it'll go off the rails.

I loved Superpowers and evangelized it heavily.

This week I removed it because it now gets in the way of the frontier models.

I don't know if its still the case anymore since 1.3 but Ghostty did have a documented issue with Claude causing resource issues.

Uggggg I just implemented Better Auth for our new product - time to start looking for backup plans. I used to be a huge Vercel fanboy but everything they have done in the last few years turns into a complicated mess.

I have found a different model should be used to do the review - like if Claude did the code, Codex should review. Models reviewing their own code is a recipe for disaster.

The liquidation event is unattainable at Zombicorn!

React was a godsend vs dealing with the Angular $digest loop

This website seems to have been generated by Codex - I asked Codex to create an HTML overview of a feature for my team and it made an overly produced monstrosity - complete with the same large stat boxes that were for the most part devoid of meaningful information - using the same font, colors, layout, hero section, etc. It was also terrible on mobile just like this is.

In the end I had Claude produce a one-page html file that was 95% of the way there and it took minor editing to clearly explain the intent of the feature.

There is a fintech startup that surrounds me at my co-working place. They literally stop working and shoot the shit with each other if Claude has a hiccup.

Yesterday one asked another "how much of this deck did Claude do"? and the response was "50%". "What 50% did you do?" => "I chose the font and colors".

I loved Zed for a few years - but their insistence on not letting Claude Code use Zed as an external editor forced me to build my own IDE.

This turned out to be pretty awesome because I built something completely customized to my workflow and it has increased my productivity by several factors.

If my math is right they can acquire about 1800 (lowish end) enterprise AI-capable GPUs for $50M so exactly what are they going to do with that? Seems pretty small.

For me, iterating with Claude begins to degrade at 200k context used, by 350k it’s crossed-fingers time, by 500k it’s essentially useless. Starting a fresh context after 300k is usually the best move imho. I wonder if people are hitting a case where Claude becomes both dumb and increasingly more expensive, essentially a doom loop.

I have 0 problem with this. Everybody who was using a Pro subscription with OpenClaw should of expected to be living on borrowed time. The more Anthropic can do to keep the Pro subscriptions at their current price point, the better. It is the best deal in tech imho.

I am a happy user of this and have recommended my team also install it. It’s made a sizable reduction in my token use.

There was a time when his insight was relevant and spoke to a lot of people. I hope he finds peace in whatever is next.

The tips in the article on enabling vi mode and fzf keybind are worth the read imho

Their multiple rounds of VC funding are predicated on their vision of collaboration so they gotta make a go at it.

Management and product needing vision and foresight is an excellent call out. I can't help but think a lot of these self-proclaimed 9-9-6 startups are in reality 11-3-6 startups with a bunch of wasted time padding to 9-9-6.

Oh I remember a time before CDNs and a big part of your startup fundraise was to build out your own setup inside a data center.

Their burn agent mode is pretty badass, but is super costly to run.

I'm a big fan of Zed but tbf I'm just using Claude Code + Nvim nowadays. Zed's problem with their Claude integration is that it will never be as good as just using the latest from Claude Code.

These extreme rounded corners are super triggering my desktop OCD

Text on frosted glass over other text is really hard to read

We need an option to turn these “improvements” off

FWIW my system does feel more snappy and the improvements to Spotlight are nice

I love Zed but this has all the hallmarks of something being totally rushed out the door.

It works off the Claude Code SDK, which mean it doesn't support many of the built in slash commands - it doesn't support /compact, which is 100% necessary because when you use this implementation enough, you'll eventually get a "Prompt too long" error message with no ability to do anything about it. Since you can't see how far you are in the context window, it's a deal breaker, since you have to start a fresh chat and might run out of room before you can ask it to create a summary prompt for continuing.

There is no way to switch models that I can tell - I think it just picks up on your default model - and there is no way to switch to Plan mode, which has become absolutely crucial to my workflow.

I didn't see Zed picking up on problems reported in the IDE, it was defaulting to running 'tsc -b' in my directories.

At this point it's better to run a terminal inside Zed and work from there. The official response in the Zed Discord has been "talk to your local Anthropic rep" to get them to support Zed's Agent Client Protocol (ACP).

Bun has been awesome for me and my team fwiw

From the article:

> What I found interesting is how it forced me to think differently about the development process itself. Instead of jumping straight into code, I found myself spending more time articulating what I actually wanted to build and high level software architectural choices.

This is what I already do with Claude Code. Case in point, I spent 2.5 hours yesterday planning a new feature - first working with an agent to build out the plan, then 4 cycles of having that agent spit out a prompt for another agent to critique the plan and integrate the feedback.

In the end, once I got a clean bill of health on the plan from the “crusty-senior-architect” agent, I had Claude build it - took 12 minutes.

Two passes of the senior-architect and crusty-senior-architect debating how good the code quality was / fixing a few minor issues and the exercise was complete. The new feature worked flawlessly. It took a shade over 3 hours to implement what would have taken me 2 days by myself.

I have been doing this workflow a while, but Claude Code released Agents yesterday (/agents) and I highly recommend them. You can define an agent on the basis of another agent, so crusty-architect is a clone of my senior-architect but it’s never happy unless code was super simple, maintainable, and uses well established patterns. The debates between the two remind me of sitting in conf rooms hashing an issue out with a good team.

How does this compare to Google Diffusion? Diffusion writes out at seemingly the speed of thought.

I use AI to help my high-school age son with his AP Lang class. Crucially, I cleared all of this with his teacher beforehand. The deal was that he would do all his own work, but he'd be able to use AI the help him edit it.

What we do is he first completes an essay by himself, then we put it into a Claude chat window, along with the grading rubric and supporting documents. We instruct Claude to not change his structure or tone but edit for repetitive sentences, word count, correct grammar, spelling, and make sure his thesis is sound and pulled throughout the piece. He then takes that output and compares it against his original essay paragraph-by-paragraph, and he looks to see what changes were made and why, and crucially, if he thinks its better than what he originally had.

This process is repeated until he arrives at an essay that he's happy with. He spends more time doing things this way than he did when he just rattled off essays and tried to edit on his own. As a result, he's become a much better writer, and it's helped him in his other classes as well. He took the AP test a few weeks ago and I think he's going to pass.

Yesterday I threatened Gemini 2.5 I would replace it with Claude if it didn’t focus on the root of the problem and it immediately realigned its thinking and solved the issue at hand.

I had a similar conversation with my CEO today - how does the incoming crop of college grads deal with the fact AI can do a lot of entry level jobs? This is especially timely for me as my son is about to enter college.

So I ended up posing the question to Claude and the response was “figure out how to work with me or pick a field I can’t do” which was pretty much a flex.