Hacker Newsnew | past | comments | ask | show | jobs | submit | suprjami's commentslogin

Finally a believable headline about CATL.

Next week we'll be back to CATL increasing energy density by 1 million percent with a battery that charges in 3 nanoseconds.



Here is the post:

https://xcancel.com/_vkaku/status/2071469740141224272

It's mainly just an image and link to

https://github.com/guilt/3DGFX

Check the commit history for the addition of Unicode


Xcancel needs a rest sometimes - give it a rip now, ol son.

I still prefer Mistral Nemo 12B for text summarisation tasks. It has a nice style. The Mistral Small 24B is also decent. I have a YouTube transcript summariser which I like these for.

However these days I usually have Qwen 3.6 27B already loaded so I mostly just use that instead.


Same. The drop in performance can be surprisingly bad. 10Gbps becomes 5Gbps. 100Gbps becomes 20Gbps.

When building Edera (product from article), I also had the added problem of the virtual networking gap where I was bridging a 10Gbit NIC over a virtual interface, and I had weird performance bouncing between 3Gbit and the full 10Gbit. Luckily I had built networking drivers before and knew the complexities of it, and managed to profile it down to the virtual interface getting worst-case NUMA occasionally.

The part 2 is going to cover how we actually solved it, which involves every part of the system having knowledge. It's so easy to ignore but it has a massive impact on perf.


Thin wallet gang.

I carry four cards in a 3D printed sleeve which is two walls (0.8mm) thick.

When my state implements digital drivers licence I can take that down to three cards.

I just realised an elastic "card sock" would be even easier.


Not just the whole internet, but commit commercial copyright infringement and settle class action out of court with authors whose books you pirated.

https://www.authorsalliance.org/2025/09/07/the-anthropic-set...

"One rule for thee, a different rule for me." - Dario


Once again, it's called LastPass because it should be the last choice when selecting a password manager.


There is too much content and not enough time.

I can read a summary and get the gist then decide if I want to read the full thing, or I can bypass it and not interact at all.

I chose the former.

Direct example, https://thefrontpage.dev/ has got me to read many more articles which I would have otherwise skipped over.


I've been using that site a lot since it was posted on here. I loved the irony of reading the summary of this guy's rant on that page


There are many other posts here which agree with you. Filling context with what you think the model needs adds nothing and possibly just inflates context which is harmful.

A good method seems to be only make a skill or memory when the LLM gets something wrong, or if you actually observe it's always doing the same step and you can get the model to the same place with less tokens.


I’ve basically never edited a skill or memory myself. I make the LLM do it as part of the /handoff skill before I clear a session. That also includes pruning existing skills/memories and resolving any drift.

Even the /handoff skill was written by the model…


It's funny because with so many different implementations of /handoff, I wonder if anyone has benchmarked handoff-and-resume to figure out what the best performance implementation looks like.

I also imagine that varies by model.


Mine are project-specific, which is a bit annoying since I’d like it to be global but there are some project-specific additions. Maybe I’ll (ask Claude to) refactor that to be more composable.

It should be a first class feature of the harness, tbh. It kind of is with the /compact [focus] parameter but this is coarse and leaves no record. I find keeping the handoff files in the repo to be useful for historical context and later debugging.


> Filling context with what you think the model needs adds nothing and possibly just inflates context which is harmful.

The solution that I've developed is, let the agent figure things out efficiently, without inflating the context. I have what I call a smart repo that better explains this at

https://github.com/gitsense/smart-ripgrep

The basic idea is, when the agent does a ripgrep it gets back files + matching lines + context.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: