HackerTrans
TopNewTrendsCommentsPastAskShowJobs

anonfunction

no profile record

Submissions

The Overnight Test

plud.net
1 points·by anonfunction·il y a 18 jours·0 comments

Eve, an open-source agent framework

vercel.com
3 points·by anonfunction·il y a 24 jours·2 comments

Anthropic warns that AI could soon escape human control

abc7news.com
3 points·by anonfunction·le mois dernier·2 comments

[untitled]

1 points·by anonfunction·le mois dernier·0 comments

Show HN: Headless terminal in zig allows AI agents to use interactive CLIs

hty.sh
1 points·by anonfunction·il y a 2 mois·1 comments

Show HN: Headless terminal - Allow agents to run any interactive TUI or CLI

github.com
3 points·by anonfunction·il y a 3 mois·1 comments

Show HN: Is Hormuz open yet?

ishormuzopenyet.com
484 points·by anonfunction·il y a 3 mois·209 comments

Show HN: macOS menu bar app that monitors your Ethernet connection status

github.com
2 points·by anonfunction·il y a 8 mois·2 comments

Show HN: Asxiv.org – Ask ArXiv papers questions through chat

asxiv.org
161 points·by anonfunction·il y a 10 mois·24 comments

comments

anonfunction
·il y a 18 jours·discuss
This is something I've been working on exposing to AI labs through my startup LatentEvals[1], and found similar results in other industries from lending to insurance claims.

Happy to share some sample reports if anyone is interested!

1. https://www.latentevals.com/
anonfunction
·il y a 24 jours·discuss
There are multiple "sandbox backends"[1] available besides Vercel currently. I'm sure more will follow, and it's open-source so you could always implement your own.

1. https://eve.dev/docs/sandbox#backends
anonfunction
·le mois dernier·discuss
One of the preeminent Zig software projects, Tigerbeetle[1], has a great website[2] and markdown file[3] for what they call TigerStyle.

It's honestly a great read as a human but also I packaged it as a skill and saw coding agent improvement, especially around memory usage.

1. https://tigerbeetle.com/

2. https://tigerstyle.dev/

3. https://github.com/tigerbeetle/tigerbeetle/blob/main/docs/TI...
anonfunction
·le mois dernier·discuss
Love these types of projects, really useful and helpful. Sharing with my daughter!
anonfunction
·il y a 2 mois·discuss
I'm the creator of hty, as part of my work for building custom eval suites at LatentEvals.com I found that AI agents struggled with interactive CLI / TUIs and would resort to setting flags that may be outdated or not exist at all.

I needed a way for AI agents to use all the software that humans do, things like htop, k9s, create-next-app, and even nethack.

How it works: hty wraps any interactive cli in a persistent PTY session. Your agent "sees" the rendered terminal the way you do and types the way you would. I've had a lot of success with agents being able to get through interactive npx setups, play terminal games, and create logical commits from a bunch of work in an long claude code session by using git add -p for interactively patching the git stage.

It's available to use as a simple skill so it works for almost all agents, but you can also use it as the human via the CLI. It's written in zig and built on top of libghostty.
anonfunction
·il y a 2 mois·discuss
[dead]
anonfunction
·il y a 2 mois·discuss
I've been doing bias and misaligned behavior research, creating custom private eval suites to test and compare models. Claude Opus 4.7 is heavily biased and presents clear regulatory and reputational risk.

It seems the initial product footprint tries to sidestep this problem by not giving the agents control on who to lend to or which applications to approve. Even so I think it's quite an optimistic read on their end. Happy to share reports to anyone who's interested ([email protected]), especially if you work at a frontier model lab and are interested in plugging my evals into your RL systems!
anonfunction
·il y a 3 mois·discuss
Author here, I built this because my agents could not use TUI or interactive CLI software. Think puppeteer for TUIs.

If you've ever asked Claude Code, codex, opencode, etc... to make logical commits from a bunch of changes you might have seen them struggle with moving files around, deleting files when a simple `git add -p` would have let them work through the changes interactivly. ht (the binary name) allows them to spawn their own terminal and drive it similar to puppeteer, sending keys, viewing a snapshot of the terminal and making a decision.

Some other use cases are also solved from CI/CD to making nice demos (it can export images or the format used by asciicast for making videos of the session.

It's powered by libghostty so it has support for all the stuff a modern terminal can do (full color, mouse clicks, etc...) and I've had a lot of fun letting claude run wild and even play games like nethack.

Happy to answer questions, and of course let me know if you run into any issues!
anonfunction
·il y a 3 mois·discuss
Fourth thing in a row they've announced that I wanted to try and couldn't.

Previous comment with the prior 3: https://news.ycombinator.com/item?id=47794419
anonfunction
·il y a 3 mois·discuss
Start designing at claude.ai/design.

That link is redirecting me to https://claude.ai/404, anyone else?
anonfunction
·il y a 3 mois·discuss
Thanks, I was already on the latest claude code, I just restarted it and now it's showing 4.7 and xhigh.

xhigh was mentioned in the release post, it's the new default and between high and max.
anonfunction
·il y a 3 mois·discuss
That sets it to opus 4:

/model claude-opus-4.7 ⎿ Model 'claude-opus-4.7' not found

/model claude-opus-4-7 ⎿ Set model to Opus 4

/model ⎿ Set model to Opus 4.6 (1M context) (default)
anonfunction
·il y a 3 mois·discuss
Seems they jumped the gun releasing this without a claude code update?

     /model claude-opus-4.7
      ⎿  Model 'claude-opus-4.7' not found
anonfunction
·il y a 3 mois·discuss
It seems they nerf it, then release a new version with previous power. So they can do this forever without actually making another step function model release.
anonfunction
·il y a 3 mois·discuss
Same, if we're punished for being on the highest tier... what is anthropic even doing.
anonfunction
·il y a 3 mois·discuss


     /model claude-opus-4.7
      ⎿  Model 'claude-opus-4.7' not found
Just love that I'm paying $200 for models features they announce I can't use!

Related features that were announced I have yet to be able to use:

    $ claude --enable-auto-mode 
    auto mode is unavailable for your plan

    $ claude
    /memory 
    Auto-dream: on · /dream to run
    Unknown skill: dream
anonfunction
·il y a 3 mois·discuss
A little off topic, but did Anthropic distill from an older OpenAI model? All the sudden over the last few days I'm getting a ton of em dashes in claude code responses!
anonfunction
·il y a 3 mois·discuss
It gets really fun when you prompt them to update their BOT.md, also they get access to previous run results so they continually "learn" from mistakes or investigate changes.
anonfunction
·il y a 3 mois·discuss
This is very cool, I just wonder where they get the crossing data!
anonfunction
·il y a 3 mois·discuss
Thanks for sharing, I think it's kind of a different type of system although a lot of similarities for sure.

I made botctl explicitly to not have to talk to my agents, I wanted them running autonomously based on their BOT.md file's prompt / goals / skills.