Viewing profile — rescbr
rescbr
HN member- Joined
- Mon, Sep 21, 2015, 1:49 PM UTC
- HN karma
- 665
- Public activity
- 385 items
- HN profile
- View on Hacker News ↗
About rescbr
No profile information was provided.
Recent public activity
-
comment
Comment #49252618
Agreed. I was a middle-schooler in the 2000's, had my own PC in my own bedroom, we had broadband access and I, of course, was exposed to porn while I was trying to download cracks …
-
comment
Comment #49248673
AI doesn't get tired. I can tell it to profile the application and find quick wins and it usually does a decent enough job.
-
comment
Comment #49183259
Sure, but you can review the git repo's content/commits in plain text, while curl-pipe-bash would require you to reverse engineer the binary that's downloaded. If somebody hacks th…
-
comment
Comment #49182522
I personally also don't like this, so use cargo to install it, it's in the readme. Takes a reasonable time to build on my X220, but on a modern computer it is plenty fast. cargo in…
-
comment
Comment #49182268
I'm using maki ( https://maki.sh ), it has 1, 2 and 3.
-
comment
Comment #49137917
This is definitely not my experience with GLM-5.2. It is writing pretty good ARM SIMD code. It also is an excellent radare2/rizin/ghidra driver as well. Maybe it's because its ~ cy…
-
comment
Comment #49123826
> questions about the modern Chinese history, to which a Chinese LLM will not answer This has been debunked here on HN so many times. The Chinese open models do answer the hairy Ch…
- comment
-
comment
Comment #49111999
I'm Brazilian and I had never connected "insha'Allah" to "oxalá". Wow, TIL. At least we were taught in school that if a word starts with "al" then there is a big chance it has root…
-
comment
Comment #49078272
Still, somebody heavily funded this thing for too long, and I very much doubt that we don't have the surveillance apparatus in place today for these things to get unchecked. Stuff …
-
comment
Comment #49078175
That's why you don't run the model at low quantization
-
comment
Comment #49009116
I also make nerdy jokes/puns, and I had similar experiences with beneficial model steering that such puns create. It's interesting how more loose/informal prompting achieves good r…
-
comment
Comment #49007788
They claimed the model was PhD-level, but they never mentioned the university the model graduated from... :)
-
comment
Comment #48996243
I currently have a free trial AI Pro subscription that will run out next month. If it weren't for the $10 GCP credit, I'd straight away cancel it. I don't see enough value in Gemin…
-
comment
Comment #48971381
Where are you sourcing the API from? I have zero quality issues on Z.ai Coding Plan and maki.sh as the coding agent, but I've seen many reports on 3rd party providers that they hos…
-
comment
Comment #48971338
I imagine they're not spying for fun...
-
comment
Comment #48954706
I feel the same. I feel Anthropics' raw models are excellent, but Claude Code's bloat make them lose some potential. This and I very much miss reading the chain of thought. At leas…
-
comment
Comment #48954600
Happy to disagree with you. There are many examples of the US using the state espionage machinery for private purposes. The extent of "private" is debatable given the US as a natio…
-
comment
Comment #48914388
You can trade-off cable shielding for electronics power and corresponding heat to encode/decode stuff. Ethernet is notoriously power hungry, but I bet you can use a phone cable and…
-
comment
Comment #48914211
And then there are the crappy devices that aren't compliant with USB PD and only charge with a USB-C to USB-A cable.
-
comment
Comment #48912886
For me it depends, if I simply take the answer from the LLM it goes straight into the shortest memory neurons my brain has. Now, if I go back and forth with the LLM to say, taking …
-
comment
Comment #48912707
I had a professor who polled the class if we preferred our exams to be open book or not. First year of undergrad. The midterm was open book, he even shared the previous year's exam…
-
comment
Comment #48908848
Exactly! It got so easy nowadays to use AI to setup scenarios since the busy work of writing code/test harnesses and setting things up for the benchmark is done by the machine. The…
-
comment
Comment #48877997
For me, them allowing API usage on coding plans so we can use any harness, and returning the full unabridged reasoning back are how they earned my trust.
-
comment
Comment #48877920
Weird. I have seen it asking the harness to do `find ~ -type f | grep` to try and find my agent configuration .json file when I asked it to add a MCP server. Stupid, but they weren…