HackerTrans
TopNewTrendsCommentsPastAskShowJobs

thehamkercat

384 karmajoined 3 yıl önce
https://github.com/thehamkercat

- [email protected]

Submissions

1-Click RCE in ClawdBot (Openclaw/Moltbot)

github.com
1 points·by thehamkercat·5 ay önce·0 comments

Ask HN: Any Microsoft employees/devs here? What's happening to Microsoft?

111 points·by thehamkercat·6 ay önce·83 comments

[untitled]

5 points·by thehamkercat·10 ay önce·0 comments

comments

thehamkercat
·4 gün önce·discuss
If LLMs are so good and productive, why doesn't everyone write native apps for things like this?

zed is pretty good, i don't think we need a non-native editor now
thehamkercat
·6 gün önce·discuss
Would've resulted in a positive response from people if you just did your work and didn't brag about your "patent pending" stuff
thehamkercat
·24 gün önce·discuss
Kimi K2 had a vendor verifier: https://github.com/MoonshotAI/K2-Vendor-Verifier

(there's a table which shows comparison between vendors)

Also, it seems there's a general one as well (for all kimi models?): https://github.com/MoonshotAI/Kimi-Vendor-Verifier
thehamkercat
·geçen ay·discuss
for those wondering: https://xkcd.com/1172/
thehamkercat
·3 ay önce·discuss
RX7900 XTX has 24GB
thehamkercat
·3 ay önce·discuss
They're milking the final drops, before LLMs become so good that they'll write something like this in an hour
thehamkercat
·4 ay önce·discuss
https://code.claude.com/docs/en/env-vars
thehamkercat
·4 ay önce·discuss
"Coded by OpenClaw" written on PCB

was this necessary? could've said "Code written by LLM" or something
thehamkercat
·4 ay önce·discuss
I've seen this happening with gemini
thehamkercat
·4 ay önce·discuss
GPT 5.3 codex had 400K context window btw
thehamkercat
·4 ay önce·discuss
Yep, it isn't just x; it's y
thehamkercat
·5 ay önce·discuss
Probably some kind of cache, but it's taken down, I'm getting 404, while some of my friends are still able to see it
thehamkercat
·5 ay önce·discuss
It's taken down lmao, in 1 hour
thehamkercat
·5 ay önce·discuss
let's call it clawshnikov next time
thehamkercat
·5 ay önce·discuss
> Lots of people are using openclaw

https://www.shodan.io/search?query=http.favicon.hash%3A-8055...

Indeed they are, at least 20,432 people :)
thehamkercat
·5 ay önce·discuss
> when I lean too heavily on LLM-generated code, I stop thinking about edge cases and error handling

I have the exact same experience... if you don't use it, you'll lose it
thehamkercat
·5 ay önce·discuss
GPT-5.2-codex or 5.3-codex Works pretty well for me in opencode
thehamkercat
·5 ay önce·discuss
This? https://maps.app.goo.gl/kATdsjnKnkWACzoc6
thehamkercat
·5 ay önce·discuss
Also, one more ridiculous thing

Send this to opus 4.5 or opus 4.6:

"udp you joke about hear a like would ? to"

It says: Chat paused Opus 4.6’s safety filters flagged this chat. Due to its advanced capabilities, Opus 4.6 has additional safety measures that occasionally pause normal, safe chats. We’re working to improve this. Continue your chat with Sonnet 4.

what???? "Due to its advanced capabilities" ???

Due to it's advanced capabilities it didn't get the joke?
thehamkercat
·5 ay önce·discuss
The "50ms" number was measured by me and you can literally try it on your system as well. it will likely be faster than 50ms

Do you have a proof that gpt-5.2 or 5.3 codex takes 2 hours for the same problem that sonnet/opus4.5/4.6 take 5 minutes to solve? (I use both anthropic and openai models daily almost equally, and i'm not relating to what you said)

Sure codex-cli lacks way-too many features compared to claude-code (I use opencode), but your statement implies that openai models are absolute garbage (2h vs 5m to solve a problem)