Hacker News

points by agentdev001 2 days ago | 0 comments

For those keeping score, this probably isnt exhaustive- but here's some greatest hits;

#55743: Claude Max account email auto-injected into LLM context with no opt-out - May 3, 2026 https://github.com/anthropics/claude-code/issues/55743

#72518: Anthropic embedded spyware in Claude Code - June 30, 2026 https://github.com/anthropics/claude-code/issues/72518

#21151: No indication of WHICH file for READ tool - January 27, 2026 https://github.com/anthropics/claude-code/issues/21151

#42796: Claude Code is unusable for complex engineering tasks with the Feb updates - April 2, 2026 https://github.com/anthropics/claude-code/issues/42796

#73408: AFK auto-continue on unanswered AskUserQuestion is undocumented and has no opt-out - July 2, 2026 https://github.com/anthropics/claude-code/issues/73408

(Also worth a mention, OpenCode PR #18186: anthropic legal requests - March 19, 2026 https://github.com/anomalyco/opencode/pull/18186)

Edit: Oh, and determistic hooks not firing.

[–] nullbio 2 days ago

Here's some more greatest hits: https://clawd.rip - a whole site dedicated to them. Unfortunately the owner seems to have stopped updating it though.

[–] roboyoshi 1 day ago

I love that it's made with AI/LLM, maybe even claude itself. Even the site that lists the flaws of the system is made with that system. Simply shows me that people are not scared off by all those flaws.

[–] kbr- 1 day ago

System having flaws does not imply system is useless. Linux has many flaws, we still use it and love it.

[–] neya 2 days ago

Claude also has the highest number of apologists on here, so watch them come up with every possible explanation of why Claude can do no wrong. You can already see the top comment brush the issue off like it is nothing wrong.

[–] foobar_______ 1 day ago

So true. They come crawling out of every hole to defend Claude. It’s absurd and frankly disgusting.

People have put so much weight and sense of self worth into choosing “the best” or most pure LLM. It’s like football teams or religion to these people.

[–] beeandapenguin 2 days ago

> deterministic hooks not firing.

We went from building skyscrapers to building a house of cards.

[–] partyficial 2 days ago

using an imaginative tool to do a deterministic task is more idiotic than... i can't come up with a metaphor.

LLMs were meant to be the ministers, not the king.

[–] kamban 2 days ago

Treating them like kings was our mistake in the first place. Give it another year, we're going to see a lot more blunders.

[–] teiferer 2 days ago

Both things true but not actually the same.

Or would you be fine with a deterministic king?

[–] faidit 1 day ago

Generally speaking, yes it would be preferable to a fickle or arbitrary king.

[–] teiferer 1 day ago

Preferring sth bad over sth worse is not the same thing as being fine with the former.

[–] bunderbunder 1 day ago

I’m honestly fascinated by how our profession is simultaneously having something of a crisis over all these arbitrary code execution vulnerabilities that keep getting found, and totally hype about explicitly granting the ability to execute arbitrary code and commands on our developer workstations over to an opaque third party service running on servers operated by companies that are now known to be unbelievably lax about cybersecurity.

[–] partyficial 1 day ago

because the camel cannot see its own hump only others'

[–] andrekandre 2 days ago

i'm sure somebody will come up with a solution; the barrier has never been lower to reinvent the flat tire...

[–] Creamsicle47 2 days ago

coding is solved. bugs not solved yet. fix incoming

[–] partyficial 1 day ago

reminds me of that Seinfeld episode -

"Anyone can just TAKE a reservation. It's the HOLDING..."

"Anyone can just CODE a program. It's the TESTING..."

[–] Melatonic 1 day ago

Exactly. Most companies got rid of their test departments. Suspect that job will be making a big comeback