ec109685

One honesty note before my comment (yuck), it's super frustrating to read an LLM produced blog that could be 1/3 the size. Why are you talking about MCP's when comparing OpenCode and Claude Code when they both support that technology?

The only interesting thing is whether OpenCode is more effective at writing code with it's reduced system prompt.

Caching doesn’t work the way the bug reporter implies. Caches are shared (at least across the enterprise), but its key is always a function of the input before it.

We achieved significant savings simply by moving everything that varies across individuals out of the system prompt so every session starts from a cache point.

For example you never want your system prompt to start with the time that the session started. Move that to the first user message if needed.

Not true at all. I hate reading my own produced AI writing.

The issue with any AI writing is that it all sounds the same.

Once that stops being true, maybe it will be acceptable. But until then, you are left with repetitive crap. That you must wade through. Not good.

Missing gradual rollout of feature flag changes themselves. Yes, you can do percentage based rollouts for individual features but still should have ability to canary all changes before they cause an insta-sev.

Supply and demand always balance out. There is no way manufacturers aren’t going to compete away these inflated margins, as long as they feel like this demand is sustainable.

The issue is they become pay to win, which just isn’t as much fun.

There is no way a port this massive will have human code reviews.

If this succeeds, there is no stopping AI given it will have crossed the rubicon of human bottlenecks.

“Here’s a million dollars to implement WebRTC for the fourth time”

“Hell no”

“Umm…”

It actually flying: https://www.instagram.com/reels/DXrvm_LAAR8/

He would pull them away from co-pilot and the unlimited spigot of money that agentic coding brings, which is contrary to the best interests of Microsfot.

Wonder what they do for their token cache if they swap mid-session like that.

Did they nerf the model or was it changes to Claude code? I agree it got frustrating.

Great example as to why people are yearning for CSS in TypeScript. Something as simple as if() only works in Chrome and there's not a good shim story for CSS versus a more complete language, so you end up with this:

The problem: CSS can compute a number – 0 for visible and 1 for hidden – but you can’t directly use that number to set visibility. There is a new feature coming to CSS that solves this: if(), but right now it only just shipped in Chrome.

So I used a trick called type grinding. You create a paused animation that toggles visibility between visible and hidden. Then you set the animation-delay based on the computed value to determine which keyframe is used:

  animation: cull-toggle 1s step-end paused;
  animation-delay: calc(var(--cull-outside) \* -0.5s);

  @keyframes cull-toggle {
    0%, 49.9% { visibility: visible; }
    50%, 100% { visibility: hidden; }
  }

I think Anthropic just highly RL’s their model to work best with it’s Claude Code’s particular ways of going about things.

All the background capability Claude code now has makes things way more complex and I saw a meaningful improvement with 4.6 versus 4.5, so imagine other harnesses will take time to catch up.

Me too. And love pulp fiction. Just used Mr. Wolf to reference a situation at work.

Defense in depth.

Any large organization is going to have some terrible employees.

EC2 spot instance, Claude code, Prompt from Panic, Eternal Terminal.

How do they feel it’s right to never respond to GitHub issues?

Apple and Google do same thing with their silly forums.

Solvable in more than 2 but not less than 2 would be the real trick.

I use Prompt, Ever Terminal, Whisper, EC2 and Claude Code.

I can build anything with it. Having Claude on top of a terraform repo lets me fully control my infra. Claude is so good at AWS and terraform, and it even found a $3k monthly accidental spend I had running (also sent a refund request to hopefully get some credit back).

Also have a Claude driven CI workflow in GitHub to help keep everything on track.

Having full access to the Claude Code TUI is so much better than the web or iOS interface, plus everything runs on your own setup.

And agree it has replaced doom scrolling / useless new reading.

The Claude code tui is so nice. The web and iOS apps neuter it weirdly.

Claude iOS is way worse. You don’t get the full tui.

This is impressive.

Though I have found repo level claude.md that is updated everytime claude makes a mistake plus using —restore to select a previous relevant session works well.

There is no way for Anthropic to optimize Claude code or the underlying models for these custom setups. So it’s probably better to stick with the patterns Anthropic engineers use internally.

You can go to a previous session and resume from there. Plus keep updating the repo claude.md along the way:

The article info is great, but why do people put up with LLM ticks and slop in their writing? These sentences add no value and treats the reader as stupid.

This is concurrency, not language magic.

This is filesystem ops, not language-dependent.

Duh, you literally told me that the previous sentence and 50 million other times.

Travel to a hotel.

You should overlay something else rather than rely on WiFi securiry. Tailscale or a vpn, private cloud or just tls, depending on your threat model.

Something something dropbox is simple :) https://news.ycombinator.com/item?id=9224

I wish Eero offered this feature. I bring three eeros to Airbnb’s to replace their crappy WiFi with my same SID, but it would be nice if it connected back through the home internet.

They throttle.