Viewing profile — Retro_Dev
Retro_Dev
HN member- Joined
- Thu, May 29, 2025, 2:54 PM UTC
- HN karma
- 709
- Public activity
- 40 items
- HN profile
- View on Hacker News ↗
About Retro_Dev
Recent public activity
-
comment
Comment #49192157
This article is 100% AI written. The data was interesting, the commentary overly verbose and hard to gain useful insights from.
-
comment
Comment #49055315
Indeed - if you need to be absolutely confident about security and privacy, run a model locally and audit the inference software and potential tooling.
- comment
- story
-
comment
Comment #48713543
Indeed - definitely not cost effective to run it on this laptop LOL. It makes me wonder how fast we could run the model if we could fit the weights entirely within CPU cache (assum…
-
comment
Comment #48713222
I ran it on my laptop, which is a Lenovo Legion 5i (think 32 GB RAM, 4060 w/ 8 GB VRAM, you get the picture). It was a quantized model (otherwise it would not fit on my NVMe 1TB dr…
-
comment
Comment #48696536
OpenZL is nice, but it's often less useful than you think - it requires that you know the structure of your data, and don't care about inspecting that data outside of your program.…
- story
-
comment
Comment #48573052
"open source" means that the code itself (for LLMs - this is training code) is available to the general public. "open weights" means that the weights (trained over time) are availa…
-
comment
Comment #48531937
Attemping to write my own CDCL SAT solver right now. I've experimented in the past with a DP & DPLL SAT solver. I'm currently somewhat mentally stuck on how to create the derived c…
-
comment
Comment #48512813
I hope that this brings out a bunch more real study about the qualitative metrics of these models, both to increase the confidence and accessibility of local LLMs, but also to redu…
-
comment
Comment #48437409
No questions, but I really enjoyed the article - thank you for sharing. It amazes me how few vacuum tubes these early computers use, compared to the billions and trillions of mosfe…
-
comment
Comment #47820297
A gamma wavelength handheld laser would be cool; "and on this petri dish, we see a dot of cells instantaneously develop cancer"
- story
-
comment
Comment #47622455
I'm very pleased with the performance of the largest gemma4 model (which I tested through ollama). My singular data point on whether an LLM remembers things well is whether it can …
- story
- story
- story
- story
- story
-
comment
Comment #46862821
There's solid reason for the translation here; the Zig core team is aiming to eliminate duplicated code and C functions, and avoid the need to track libc from multiple sources. In …
- story
-
comment
Comment #45543626
In the theoretical world where a subset of English could be formalized and proven and compiled, the complexity of the language would reduce my willingness to use it. I find that th…
- story
- story