HackerTrans
TopNewTrendsCommentsPastAskShowJobs

afshinmeh

no profile record

Submissions

Zero: The Programming Language for Agents

github.com
3 points·by afshinmeh·2 ay önce·0 comments

Trump releases previously classified UFO files

reuters.com
4 points·by afshinmeh·2 ay önce·0 comments

Google signs classified AI deal with Pentagon

reuters.com
7 points·by afshinmeh·3 ay önce·3 comments

ClawRun – Deploy and manage AI agents in seconds

github.com
30 points·by afshinmeh·3 ay önce·9 comments

Google "6-7"

google.com
9 points·by afshinmeh·3 ay önce·2 comments

Show HN: ClawRun – Deploy and manage AI agents in seconds

clawrun.sh
2 points·by afshinmeh·3 ay önce·0 comments

Show HN: Zerobox – Sandbox any command with file, network, credential controls

github.com
141 points·by afshinmeh·4 ay önce·93 comments

Show HN: ClawRun – Deploy AI agents to secure sandboxes with one command

clawrun.sh
3 points·by afshinmeh·4 ay önce·0 comments

Show HN: "Ask AI" for Your Website

peam.ai
1 points·by afshinmeh·4 ay önce·0 comments

Show HN: ClawRun – Deploy AI agents into secure sandboxes with one command

clawrun.sh
3 points·by afshinmeh·4 ay önce·0 comments

Show HN: Peam – AI that knows your website

peam.ai
1 points·by afshinmeh·4 ay önce·0 comments

ClawRun – Deploy and manage AI agents in seconds

clawrun.sh
10 points·by afshinmeh·4 ay önce·2 comments

Most white-collar tasks will be automated by AI within 18 months

businessinsider.com
4 points·by afshinmeh·5 ay önce·4 comments

Microsoft Agent Framework

azure.microsoft.com
9 points·by afshinmeh·10 ay önce·0 comments

comments

afshinmeh
·geçen ay·discuss
Genuinely wondering though: is the problem that the patch was vibe coded, or is that no one reviewed the changes?
afshinmeh
·geçen ay·discuss
what does "LLM-native code understanding" mean in this context?
afshinmeh
·2 ay önce·discuss
I love SQLite and thanks for sharing it but there should be a "(2018)" at the end in the title:

> As of this writing (2018-05-29) the only other recommended storage formats for datasets are XML, JSON, and CSV.
afshinmeh
·2 ay önce·discuss
That's exactly how I tried to address that problem with https://github.com/afshinm/zerobox -- you control what network access (e.g. `--deny-net *.amazonaws.com`) your agent has and you also get snapshotting out of the box.

That said, using LakeFS is probably a better long term solution and I like this approach.
afshinmeh
·2 ay önce·discuss
I'm mainly looking at Rust based projects and haven't been able to find something to use out of the box, without hacky RPC/Shell execs. Curious if you have any suggestions?
afshinmeh
·2 ay önce·discuss
Sort of. My thinking is that the input to define the workflow should be anything you prefer to use (TS, Go, YAML, etc.) and the orchestrator's job is to model that and execute the job, given your deployment model.
afshinmeh
·2 ay önce·discuss
Yeah, that makes sense. I looked at a few workflow orchestrators and I'm building something that I will release soon, but my thinking is that the "workflow engine" should be an abstraction that takes the input and executes the steps. "What" you use to define that workflow is probably the SDK layer though, but I can certainly see the value in using type safe code to define as opposed to a YAML file.

I'm mainly focusing on the portability aspect of it (e.g. use TS/Python/etc. to define the workflow/steps or just simple a simple YAML file).
afshinmeh
·2 ay önce·discuss
Curious, what format would you prefer to use to represent a workflow instead of YAML?
afshinmeh
·2 ay önce·discuss
https://github.com/vivekg13186/Daisy-DAG/blob/main/backend/s...
afshinmeh
·2 ay önce·discuss
I wonder though, what about cases where you have multiple agents or LLM backends and the credentials is shared between all of them?
afshinmeh
·2 ay önce·discuss
Agreed and it's a pattern that OpenAI suggested a few days ago, too [1]. I also built a cross platform process level sandboxing that uses parts of OpenAI Codex for the same purpose [2]

[1] https://openai.com/index/the-next-evolution-of-the-agents-sd...

[2] https://github.com/afshinm/zerobox
afshinmeh
·2 ay önce·discuss
Vibe coding aside [1], it's very interesting software projects these days don't really care about adding a single test [2].

[1]: https://github.com/withastro/flue/blob/8fdf8e0e9df5bd33c3120...

[2]: https://github.com/search?q=repo%3Awithastro%2Fflue+test+pat...
afshinmeh
·3 ay önce·discuss
> It solves the problem the originating user asked it to

Interesting. And is there a mechanism to go back and "fix" the tools after they are published? What happens if the tool decided to use the "id" attribute to click on buttons and now you have a new website that follows a different pattern to find the right target?

I agree that "correctness" of a tool could have different meaning depending on the context of the problem though (e.g. would you consider OOM a correctness bug even if it addresses the user's ask?)
afshinmeh
·3 ay önce·discuss
> how do we avoid burning tokens solving the same problems over again

Letting the LLM write half baked tools is the recipe for burning more tokens.

> There's a wiki the LLM searches before solving a problem, that links saved programs for past actions to their content entry.

What's the criteria for marking an LLM written tool as useful/correct before publishing it?
afshinmeh
·3 ay önce·discuss
https://github.com/mozilla/standards-positions/issues/1067
afshinmeh
·3 ay önce·discuss
It's actually interesting to me that the author is surprised the agent could make an API call and one of those API calls could be deleting the production database.

It's a sad story but at the same time it's clearly showing that people don't know how agents work, they just want to "use it".
afshinmeh
·3 ay önce·discuss
I have been struggling with the same issue but help me understand this:

> The lack of predictable output/outcomes

How does that actually show up in practice for you? Asking because "lack of predictable output" could mean different things depending on the context.
afshinmeh
·3 ay önce·discuss
I'm adding snapshotting as well https://github.com/afshinm/zerobox/pull/21

Then you can run:

```

zerobox --snapshot -- sh -c 'echo "abc" > a'

```

and also `zerobox snapshot list/diff/restore`
afshinmeh
·3 ay önce·discuss
I agree. What would be the ideal DX from your point of view?
afshinmeh
·3 ay önce·discuss
Thanks for sharing this. I really like the idea