sunaookami

>When cargo fails to build and creates a massive amount of compile errors, you're better off having this preprocess step.

Claude already greps and tails every output by itself, a sub-agent would do the same.

Yep, I've used Pi in the past (see my other comment https://news.ycombinator.com/item?id=49908276) but I don't like the direction it went (selling out, forgetting their principles/throwing them out). And since Anthropic wants you to use Claude Code with their sub I just switched to CC again. I've only used Pi for a few months though when GitHub Copilot gave you 300 requests for like 10$.

I never hit compaction, most of my sessions are 150-300k tokens long with the longest being around 700k. Using sub-agents means that they can't use that cache, have to re-read everything and now multiply this for every sub-agent you call and it just wastes money/tokens. I also don't like how intransparent sub-agents are, I can't follow what they are doing and I can't really steer them. Claude Code has the /agents view but it's clunky and awful to use.

GPT context window is way too low for me and my last experience with it (GPT 5.6 Sol) was so awful and I hit limits way too fast that I cancelled it (and at least got my money back).

I'm no longer using Pi since it got worse IMHO and Claude subs can only be used in Claude Code but I miss the /tree feature which is perfect for first letting the model read & cache the important bits of the codebase and then start your plan from there (as long as you stay in the Cache TTL). Claude Code has /rewind but it's not as good.

I'm only using the 20$ plans.

Hah, it's the complete opposite for me :D. In Claude Code I disabled all sub-agents stuff, disabled nearly all tools but Bash, Edit, Write and WebSearch and replaced WebFetch with my own tool that doesn't summarize anything because the results were always worse with sub-agents, they always lack the necessary context and weaker models summarize bad. I also replaced the system prompt with my own that cuts a LOT of tokens, agents don't need a 10k+ system prompt anymore.

gpt-6-luna is terrible. It leaks tool calls and markers in the output like crazy, there is definitely something wrong here. gpt-5.6-terra works fine. Also, gpt-6-luna was sneakily added to the 1 mio free tokens group instead of 10 mio. like gpt-5.6-luna: https://help.openai.com/en/articles/10306912-sharing-feedbac...

And the Cloudflare dashboard is soooo slooooow and logging in takes an eternity, using Passkeys often just doesn't work ("not tied to a specific account"???) and the loging in button takes forever to be clickable because of some bot checks running in the background.

They should also improve the bookmarks and history UI, it's unusable. They redesigned the history sidebar now and it takes a lot longer to show up...

Naive and outright dangerous advice, every release fixes important security issues.

We rented VPS as kids

GPT models really have no taste huh.

Morphe just patches the YouTube app no? Then you need to still use that abomination. NewPipe/PipePipe is fast, lightweight and I couldn't care less about any "features" other than watching a video.

>invited me to a discord server

At least kids back then knew how to host their own TeamSpeak server ;) Clicking yourself a Discrd "server" is the easiest thing you can do.

They can't even use a computer, they struggle with basic computer knowledge because they grow up with closed ecosystems and most of them only have smartphones, not a desktop PC. They are called "Digital Naives" (sic) for a reason.

That's not the source code. Claude Code is proprietary.

There is no "specification", it's literally just a text file that gets loaded into context. You don't even need to write markdown. It's not that hard man.

God I miss GNOME 2... I will never forgive the GNOME devs.

Tested it in the last few hours and it's MILES better than Opus 5. Finally the output is readable again!

>with unnecessary annoying editorializing

The editor is Liam Proven, a notorious liar who doesn't care about facts and has a massive hate-boner for AI, what do you expect? I'm surprised he is still allowed to write for The Register.

That's not a reason to censor it at the state level.

This is the Claude-ism that I despise the most, when it states something that was never asked because it leaked from the prompt/context. Claude's writing has regressed so much, it's only usable for "raw coding" now.

A problem that can't be solved, you can't check every single program out there much like you can't check every single human ever even with cameras installed everywhere.

Nope.

The EU is not interested in liberating phone operating systems because it goes against their digital wallet push which forces everyone to use an attested, Google/Apple sanctioned device and operating system.

And e.g. browsers cracked down on it, removed toolbar support and powerful add-on support AND enforced signing meaning everything goes through their gatekept extension store and these problems still persist (e.g. addons changing the search provider, new tab page or homepage). Locking everything down does not help.

They autoplay the video on mute which is not banned. I don't know why news websites do it, seems like wasting traffic and should cost more than the hypothetical income from video ads?

It's still like this and now they release new versions and breaking changes way faster. Not to mention they nudge you to Expo now and outsourced nearly everything to other (outdated) dependencies and companies. Stay far away from RN if you value your sanity, it lead to my burnout.

Aero was pretty though.

You mean 7 ;)

This man has been dead for nearly 15 years, just let him be. It's time to move on.