Hacker Newsnew | past | comments | ask | show | jobs | submit | runeb's commentslogin

A particularly pronounced version of this can often be seen by letting 2 agents review and code in a loop. One agent will find some problems with the code, the other agent will address the review by adding more code.

A good human developer might see that the better way to address the review is to backtrack and pick a different approach. The ai agents seem more prone to getting stuck down bad branches of the decision tree.


Code reviews should be done by someone other than the author though, so the only thing that changes with ai generated code in that respect is the amount of it


That doesn’t conflict with my statement.

Before: One person writes the code (and likely understands it thoroughly), another person reviews the code to spot obvious mistakes or shortcomings. Now: AI writes the code, a person reviews it to spot obvious mistakes or shortcomings.

In the before case, you have a person who has a deeper understanding of the code and in the AI case, you don’t, instead you have even more code to review.

When a competent programmer is writing the code, the human written code tends to be higher quality too. So it’s not just about review quantity but the quality of code being reviewed. Some people claim the AI writes great code, but that just hasn’t been my experience yet (at least with the models I’ve tried, including Opus). They still make ridiculously bad decisions regularly.


>When a competent programmer is writing the code, the human written code tends to be higher quality too

This is a great idea, but on average is deeply untrue. Far and away most programmers today write significantly worse code than LLMs. Also LLMs are fantastic at generating high level summaries and comments in code


> Far and away most programmers today write significantly worse code than LLMs

Your experience with LLMs do not match my own. Not to say that I haven’t experienced terrible human written code where I’ve wondered what the author could possibly have been thinking, but overall, I still find LLM written code to be on the poor side.

Like, the code itself is ok, but the wider picture reasoning and abstractions are bad. It also makes really dumb decisions far too often. Or doggedly shoehorns its first idea in no matter how badly it fits.


They specifically mention "H.264, H.265, and av1 codecs, along with many others" here https://red.anthropic.com/2026/mythos-preview/


Checkout tailscale


And what about a website I want to make public? I'm just concerned about my IP being visible, like for my personal website or my searxng instance


Personally I'd just proxy it through a vm running on hertzer, linode, rackspace, etc


Tailscale Funnel, but might need a paid account


Tailscale's control plane uses Cloudflare.


Thanks, I did not know this. My Tailscale was unaffected by the outage.


I read their point as why have passwords at all when the security is you having access to your email account.


> The backup roll thrusters in use are now at risk due to residue buildup in their fuel lines

Such a human experience this probe is having


In relation to the client (AI Agent), the MCP server is serving resources like tools, but in relation to your platform that hosts the API those tools call, it is a client.


exactly, a proxy has tools but no content.


I had good results with pyannote and the following model for that use case in the past https://huggingface.co/pyannote/speaker-diarization-3.1


I believe their comment was about safety, not usability


Curiously, Scipio is also arguably one of the most famous family names from Roman Antiquity.

https://en.wikipedia.org/wiki/Scipio_Africanus


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: