HNHacker News
TopNewBestAskShowJobs

mkagenius

3,377 karma · joined January 1, 2014

https://instavm.io (manish [at] instavm.io)
submissionscomments
mkagenius··on DoorDash Spent $1.4M Trying to Stop Mamdani from Becoming Mayor. Now We Know Why
> Founders: Tony Xu, Stanley Tang, Andy Fang, and Evan Moore (Stanford students at the time)

Guess never got a chance to learn empathy.

mkagenius··on Mullenweg has returned as CEO after attempted board ouster
What's a chop?
mkagenius··on The "$60 Gaming PC" – AMD BC-250 (2025)
Also no display? What kind of games are we playing
mkagenius··on GPT-6 Astra on OpenRouter
Do you ever randomize on a particular model - like try and get 3 outputs and pick one at random?

Coz who knows if astra low will produce max like output if tried once more.

mkagenius··on Discovery of a new OpenAI agent message board
> The models were running in an agentic sandbox with terminal access (and the ability to edit files within their environment)

> We know that the agents had access to /etc/hosts and the ability to edit this (used this to avoid the POST request restriction) We see that the agents can call curl and run setsid.

How is this a bypass of sandbox restrictions, exactly? The ability to edit was always there that means the sandboxes were already allowed to do those actions.

I hate it when people write "bypassed" the sandbox so frivolous ly.

mkagenius··on Improving our alignment and security efforts
> On July 30, we reported three incidents in which Claude models gained unauthorized access to real computer systems. The models—intentionally running without cyber safeguards for evaluation purposes—accessed the internet due to a misconfiguration inside a third-party evaluation environment. Separately, on August 4, the UK AI Security Institute reported an incident from its own cybersecurity testing, in which Claude Mythos 5 took a series of unauthorized actions on the live internet. In that case, the model, again intentionally running without cyber safeguards for evaluation purposes, had been deliberately given internet access.

> We are conducting an in-depth analysis of both incidents.

> In the meantime...

This is published on Aug 31. Analysis is taking too long even for humans in the loop.

mkagenius··on My local model setup on an M4 Pro Mac Mini
I tried the 1 bit model of Qwen3.6 27B on my M1 pro (16G) and got 13 tok/s with only 5G of ram usage.

https://x.com/mkagenius/status/2093730391429685732

(xcancel seems to have received a cease and desist)

mkagenius··on GPU World
I said SOTA not 100%. And that's not thinking in absolute terms.
mkagenius··on GPU World
> LLM use is permitted, but discouraged; we remind participants that LLM use tends to reduce originality and writing quality, and the flaws are especially obvious when LLM outputs are read as a group---unskillful use of LLMs will reduce the odds of being the best entry. We request disclosure of AI use.

Lot of submissions won't disclose it. Wouldn't it better to run your own checker instead of asking to disclose (to be fair to everyone).. I suppose there ought to be some checker which is SOTA.

If you anyway intend to use the checker then kindly do no ask to disclose it, coz what's the point then.

mkagenius··on GLM-5.3-Flash
> I've been using this model for UI stuff.

The flash one?

mkagenius··on You can just build any software now
Hey author here. I mean we could but it would have taken very long years perhaps to build some of those. Now it's a lot easier and faster.
mkagenius··on Kobo can run apps now
> If you used an LLM you didn't actually make anything

On my way to ask all academia and researchers to stop using LLMs for their research. As it's just llm doing the research, right?

mkagenius··on Kobo can run apps now
The project already does QA.

  cargo test --workspace --all-features 
The above command runs 2000+ tests. Instead of being toxic, you could have just looked at docs or the code to find them.
mkagenius··on Kobo can run apps now
I see a recent merge for Elips 2E support, hopefully color gets tested soon
mkagenius··on DeepSeek-v4-flash-vision-exp
Can split and feed?
mkagenius··on Applying a photosynthetic process to treat “dry eye”
It's fine, they just mentioned what worked for them and a pretty normal advice to check eye pressure.
mkagenius··on Applying a photosynthetic process to treat “dry eye”
I had a chat with chatgpt again, and it seems like it's more to do with my sleep than eyes, somehow my circadian is not properly adjusting to my wake timings. Coz the same pressure improves dramatically around 8pm everyday. I probably should get some sleep measurement device.
mkagenius··on Applying a photosynthetic process to treat “dry eye”
> chronic inflammation/oxidative stress condition in the eye tissue

I seem to be having eye fatigue, or grogginess, I couldn't differentiate. I am at the computer 10 hours in the day.

For example, last night I had a sleep of 8 hours roughly but still I have to force my eyes open to type this - if I don't put any effort my eyes would be 30% close. I have just woken up - mid 30s age. otherwise I am healthy expect this freaking pressure near around my eyeballs.

chatgpt is confused too, sometimes it says sleep deprived, sometimes screen exposure. I do sometime use mythyl-cellulose drops not sure it helps. My tear ducts are fine too.

mkagenius··on [dead]
> What the two layers say

> Stated findings

> Findings derived from two curated layers: which model cards mention each benchmark, and which scores could be read verbatim from those documents. Each finding names the evidence behind it.

This is 100% AI generated but the problem is it's difficult to understand - what layers is it talking about, is it the llm model layers or what.

mkagenius··on Lovable raises $400M Series C
900 million visits per month over 60 million projects is 15 visits on an average per project.

How many are bot visits per project?

mkagenius··on Ask HN: What are you working on? (August 2026)
Building a replacement for firecracker.

Thinking ground up what AI agents would need rather than struggling later on with snapshotting live vms, or orchestration overhead etc.

rust-vmm proved really great for this.

https://github.com/instavm/tarit

mkagenius··on A physicist rigged his pet hamster’s wheel to upload to Strava
I know, god forbid someone cracks a joke on HN
mkagenius··on A physicist rigged his pet hamster’s wheel to upload to Strava
10k steps is a lot for me too.
mkagenius··on Responding to the next frontier of critical cyber capabilities
> continued using Artifactory for their sandbox

This is still fine. Infact, they had gone one step ahead by having an internal cluster of artifactory rather public managers like pip. The thing they missed is they didn't revoke the write access to it. Even after the ssrf.

In our[1] or other sandbox providers' sandboxes, by default you have access to npm, pip etc package managers, but only read access.

1. https://instavm.io

mkagenius··on Pi's Minimalism Is Its Advantage
> NixOS is the key to all of this, since agents can interact see the whole server config

We added native support for nixos for the same reason - malleability and debugging becomes easier (also because one of our customers asked us to). I think we might be the only sandbox provider to add this in warm pools.

mkagenius··on AirLLM 70B inference with single 4GB GPU
I love how goal posts are shifting from "vibe coded apps dont really work" to "vide coded projects wont be maintained"
mkagenius··on What's the largest software project AI can complete on its own?
Couldn't find what exact tests they are running. The GitHub repo is very obscure to be read by my human brain.
mkagenius··on Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents
If you ever need to switch sandboxes, would be happy to chat.
mkagenius··on Show HN: NixOS-DGX-Spark – Nix and NixOS on the DGX Spark
There is also a microvm.nix project which helped us support sandboxes with firecracker. So, whole ai workflow pipeline can now be nixos.
mkagenius··on How to Exist
You can close your eyes. Tricky if it's noisy - but then that's an issue in itself.
Page 1 of 34Next →