HackerLangs
トップ新着トレンドコメント過去質問紹介求人

noperator

no profile record

投稿

Pelican, or pelican't? A hint at Claude evals

noperator.dev
4 ポイント·投稿者 noperator·28 日前·0 コメント

You can just say it

noperator.dev
3 ポイント·投稿者 noperator·先月·0 コメント

Show HN: Cagent – Agent in a Cage

github.com
2 ポイント·投稿者 noperator·4 か月前·0 コメント

My AI got a GitHub account

maragu.dev
1 ポイント·投稿者 noperator·6 か月前·0 コメント

Sift or Get Off the PoC: Vulnerability Research via Information Retrieval

arxiv.org
1 ポイント·投稿者 noperator·6 か月前·0 コメント

Computing, Convivially

v5.chriskrycho.com
2 ポイント·投稿者 noperator·6 か月前·1 コメント

コメント

noperator
·7 日前·議論
Leanstral 1.5 has 6B active parameters. How many parameters does GPT-5.5 have?
noperator
·17 日前·議論
Yes, I did end up figuring out a clean way to allow normal reasoning inside <think> and then force JSON _after_ the closing </think>. Example here: https://gist.github.com/noperator/6c711ab19027ea8056442df839...
noperator
·18 日前·議論
Having some success while testing this model out as a replacement for GPT-5 nano in source code security review. Running on RTX 3090 (24 GB VRAM) via vLLM. It's not great on structured output (as noted in the model card) but I'm working around that in my harness.
noperator
·4 か月前·議論
> compute isolation means nothing if the sandbox can freely phone home.

Here's a project I've been working on to address the network risk. Uses nftables firewall allowing outbound traffic only to an explicit pinned domain allowlist (continuously refreshes DNS resolutions in the background).

https://github.com/noperator/cagent
noperator
·6 か月前·議論
Digital technologies can be terribly destructive, but they can also be gloriously empowering. How do we shape them into tools for conviviality rather than means of domination?