Hacker News: ljosifov

New comment by ljosifov in "Hammerspoon"

ljosifov — Sat, 14 Mar 2026 12:17:38 +0000

Glad to see other people using it. Saved my life, was going crazy click-clicking to nab the right window. Now Cmd-1..9 brings to focus a window of my chosen application. (Chrome) In case it helps someone else, myself and Codex iterating over time https://github.com/ljubomirj/dotfiles/blob/main/.hammerspoon.... Cmd-1..9 switches over focuses to a particular window, Cmd-0 presents an (ugly; but suffices) dialog box to select the window with arrows (of the App of interest - Chrome for me atm) to switch to. But more important - to see what window what Window name is recalled by the particular Cmd-1..9 shortcut. Option-arrows shuffle window-to-key ordering. I right-click-Name Window my windows. Think back now - on restart they may even be preserved?? Don't recall re/naming them manually recently. (possible I've forgotten though)

New comment by ljosifov in "How to run Qwen 3.5 locally"

ljosifov — Sun, 08 Mar 2026 11:38:12 +0000

Say more please if you can. How/why is ik_llama.cpp faster then mainline, for the 27B dense? I'd like to be able to run 27B dense faster on a 24GB vram gpu, and also on an M2 max.

New comment by ljosifov in "GLM-5: Targeting complex systems engineering and long-horizon agentic tasks"

ljosifov — Wed, 11 Feb 2026 15:54:01 +0000

Everyone should do the calculation for themselves. I too pay for couple of subs. But I'm noticing having an agent work for me 24/7 changes the calculation somewhat. Often not taken into account: the price of input tokens. To produce 1K of code for me, the agent may need to churn through 1M of tokens of codebase. IDK if that will be cached by the API provider or not, but that makes x5-7 times price difference. OK discussion today about that and more https://x.com/alexocheema/status/2020626466522685499

How to Run Local LLMs with Claude Code and OpenAI Codex

ljosifov — Thu, 29 Jan 2026 21:38:08 +0000

Article URL: https://unsloth.ai/docs/basics/claude-codex

Comments URL: https://news.ycombinator.com/item?id=46816996

Points: 2

# Comments: 0

New comment by ljosifov in "Ask HN: Share your personal website"

ljosifov — Wed, 14 Jan 2026 19:48:34 +0000

https://ljubomirj.github.io small personal ~/public_html

When competition leads to human values by Beren Millidge [video]

ljosifov — Wed, 14 Jan 2026 07:16:35 +0000

Article URL: https://www.youtube.com/watch?v=ua67aXBP76k

Comments URL: https://news.ycombinator.com/item?id=46613277

Points: 1

# Comments: 0

New comment by ljosifov in "I rebooted my social life"

ljosifov — Thu, 01 Jan 2026 16:48:00 +0000

+1. For every one like the author of the blog post, it's likely to be another one in the opposite direction. But they will be unlikely to write a post about that. I too found weighting 'spend time with human persons v.s. with my own thoughts, or programming and writing, or reading a paper or a post, or listening to a podcast while walking in nature' lately come down on the side away from humans. So far - it's been way more interesting. When/if that changes and becomes boring - will think what next and change.

A new way to extract detailed transcripts from Claude Code

ljosifov — Fri, 26 Dec 2025 10:36:00 +0000

Article URL: https://simonwillison.net/2025/Dec/25/claude-code-transcripts/

Comments URL: https://news.ycombinator.com/item?id=46390913

Points: 3

# Comments: 0

New comment by ljosifov in "GLM-4.7: Advancing the Coding Capability"

ljosifov — Tue, 23 Dec 2025 10:12:27 +0000

I imagine - and sure hope so - everyone trains on everything else. Distillation - ofc if one has bigger/other models providing true posterior token probabilities in the (0,1) interval (a number between 0 and 1), rather than 1-hot-N targets that are '0 for 200K-sans-this-token, and 1 for the desired output token' - one should use the former instead of the latter. It's amazing how as a simple as straightforward idea should face so much resistance (paper rejected) and from the supposedly most open minded and devoted to knowing (academia) and on the wrong grounds ('will have no impact on industry'; in fact - it's had tremendous impact on industry; better rejection wd have been 'duh it is obvious'). We are not trying to torture the model and the gpu cluster to be learning from 0 - when knowledge is already available. :-)

New comment by ljosifov in "A guide to local coding models"

ljosifov — Tue, 23 Dec 2025 08:55:45 +0000

Nah - given the ergonomics + economics, local coding models are not atm that viable. I like all things local even if just for safety of keeping healthy competitive ecosystem. And I can imagine really specialised uses cases where I run an 8B not-so-smart model to process oodles of data on my local 7900xtx or similar. Got older m2 mbp with 96gb (v)ram and try all things local that fit. Usually LMStudio for the speed add in MLX format models on ASI (as end point; plus chat for vibes test; LMStudio omission from the OP blog post makes me question the post), or llama.cpp for GGUF (llama.cpp is the OG; excellent and universal engine and format; recently got even better). Looking at how agents work - an agent smarts of Claude Code or Codex in using the tools feels like it's half its success (the other half the underlying LLM smarts). From the training on baked in 'Tool Use & Interleaved Thinking' on the right tools in a right way, to the trivial 'DONOTDO bad idea to fill your 100K useful context with random content of multi-MB file as prompt'. The $20/mo plans are insanely competitive. OpenaI is generous with Codex, and in addition to terminal that I mostly use, there is the VSCode addon as well as use in Cline or Roo. Cursor offers in-house model fast and good, insane economy reading large codebases, as well BYOK to latest-greatest LLMs afaik. Claude Code $20/mo is stingy with quotas, but can be supplement with Z.ai standing in - glm-4.7 as of yesterday (saw no difference glm-4.6 v.v. sonnet-4.5 already v.good). It's a 3 lines change to ~/.claude/settings.json to flip Z.ai-Anthropic back and forth at will (e.g. when paused on one to switch to the other). Have not tried the Cerebras high tok/s but wd love to - not waiting makes a ton of difference to productivity.

New comment by ljosifov in "What Does a Database for SSDs Look Like?"

ljosifov — Sat, 20 Dec 2025 12:01:26 +0000

Not for SSD specifically, but I assume the compact design doesn't hurt: duckdb saved my sanity recently. Single file, columnar, with builtin compression I presume (given in columnar even simplest compression maybe very effective), and with $ duckdb -ui /path/to/data/base.duckdb opening a notebook in browser. Didn't find a single thing to dislike about duckdb - as a single user. To top it off - afaik can be zero-copy 'overlayed' on the top of a bunch of parquet binary files to provide sql over them?? (didn't try it; wd be amazing if it works well)

We present Olmo 3, our next family of open, leading language models

ljosifov — Thu, 20 Nov 2025 22:42:48 +0000

Article URL: https://twitter.com/natolambert/status/1991508141687861479

Comments URL: https://news.ycombinator.com/item?id=45998890

Points: 1

# Comments: 0

New comment by ljosifov in "Europe is scaling back GDPR and relaxing AI laws"

ljosifov — Wed, 19 Nov 2025 16:09:05 +0000

So far so good - and I say this as one voting remain. The only gripe I have is that our domestic doomers were even more stupid than the EU ones. Ours were the progenitors of many of EU dumb ideas. So even outside EU, we in the UK not only did not repeal the utterly imbecilic laws we inherited. No - we added even more stupid laws. Consequence being people are put in jail for writing stuff on the Internet. I hope someone puts in jail the lawmakers that voted for these laws. To the cheering of and with public support, it must be said. It was not without consent, it was not only bi-party, but omni-party consent.

New comment by ljosifov in "Zoo of array languages"

ljosifov — Tue, 14 Oct 2025 17:20:44 +0000

Yeah - IDK why it never makes it to these lists. R too. Matlab being 2D matrix first/default gets it right for me there. IK matrices trivially translate to arrays, still: find 2D to be extra expressive on human level, for zero price paid. I get it it's all the same to the cpu. 2D rows-columns rectangle of data being the simplest data structure both necessary and sufficient covering a 1) matrix 2) spreadsheet 3) SQL table 4) directed graph of nodes and edges. (in the past I've read someplace that lists are for pie eaters, but wouldn't know myself

New comment by ljosifov in "Don't avoid workplace politics"

ljosifov — Thu, 02 Oct 2025 10:15:08 +0000

Yes - so telling hard truths is not for the benefit of the listener, it's for the benefit of the speaker mostly. That's a major point: if I see, but I don't tell, if I have private truths and public lies, it's one small victory for untruths. However much I think I'm not - I'm co-opted in the big lie machine. There is quite a lot of experience with this acquired during the totalitarian communist regimes that existed in eastern Europe <1990s. And a minor point is: the listener may switch off, but a minuscule part of the message may make it's way. May implant a tiny seed of doubt, admittedly very very unlikely. But it's not totally futile. Even if the speaker may decide the price to be paid is too high, for too little gain. (lots of the time)

New comment by ljosifov in "Imgur pulls out of UK as data watchdog threatens fine"

ljosifov — Thu, 02 Oct 2025 01:38:08 +0000

Iceland - sorry for the confusion. (poor spelling)

New comment by ljosifov in "Imgur pulls out of UK as data watchdog threatens fine"

ljosifov — Wed, 01 Oct 2025 13:24:22 +0000

Eh - for the world's audiences: EU is not Europe. I geddit how/why why people equate eu == europe - it would simplify things for all, one niggle less to consider. But - it ain't so, for better or worse. There are countries in Europe, that can't be members of the European Union, or could be, but don't want to be members. (e.g. UK, probably Island, Switzerland, some of the Nordics) There are no countries in the European Union, that are not part of Europe. So EU <= Europe. (unsurprisingly)

New comment by ljosifov in "Updates to Consumer Terms and Privacy Policy"

ljosifov — Sat, 30 Aug 2025 09:39:11 +0000

I think you are correct there - the majority of the public don't care. They just try to get about doing their daily business and act the best they can under circumstances. So we just click "Accept" to any popup banner make it go away, accept "All cookies" 100 times every day, use Google mail/map/photos/drive and that all involves giving away data, even if in words we say we don't want to give data. So yes obviously the public by necessity act in a rational way, doing cost-benefit analysis. While a cadre of privacy obsessives have made my life worse by lobbying and having their bad ideas codified in the UL laws. Wrote about my experience in the UK medical systems here https://news.ycombinator.com/item?id=45066321

New comment by ljosifov in "If you have a Claude account, they're going to train on your data moving forward"

ljosifov — Sat, 30 Aug 2025 09:15:24 +0000

I am a little bit worried, for sure. But I think that's small extra risk on my side, for small extra gain for me personally, but large extra gain for the wider group I belong to (ultimately - all of humanity) in the sense of working towards ameliorating the "tragedy of the commons".

On the personal side. Given the LLM-s have not got the ground truth, everything is controlled hallucination, then - if the LLM tells you an imperfect version of my email or chat, you can never be sure if what the LLM told you is true, or not. So maybe you don't gain that much extra knowledge about me. For example, you can reasonably guess I'm typing this on the computer, and having coffee too. So if you ask the LLM "tell me a trivial story", and LLM comes back with "one morning, LJ was typing HN replies on the computer while having his morning coffee" - did you learn that much new about me, that you didn't know or could guess before?

On the "tragedy of the commons" side. We all benefit immensely from other people sharing their data, even very personal data. Any drug discovery, testing, approval - relies on many people allowing their data to be shared. Wider context - living in a group of people, involves radiating data outwards, and using data other people emit towards myself (and others), to have a functioning society. The more advanced the society, the more coordination it needs to achieve the right cooperation-competition balance in the interactions between ever greater numbers of people.

I think it's bad for me personally, and for everyone, that the "data privacy maximalists" had their desires codified in UK laws. My personal experience in the UK medical systems has been that the laws made my life worse, not better. Wrote here https://news.ycombinator.com/item?id=45066321

New comment by ljosifov in "Updates to Consumer Terms and Privacy Policy"

ljosifov — Sat, 30 Aug 2025 08:50:48 +0000

Yes - I meant 'impossible to difficult' to define to all people, at all times. Agree it's easy for me to define how that looks. It doesn't mean that the same is true to you. That's why I went from a very general, to very specific.

I'm saying we ended up in situation where people are lying when they say "I don't trust Google", b/c they have Gmail, use Google services - so their trust can't be zero. It's more than zero. Obviously it's a trade-off, people are pragmatic they do their cost-benefit analysis, and act accordingly. They just lie when they talk about the subject. I think it'd be better for all, if the public discussion moved from "I trust Google zero" (which is obviously untrue), to "There is cost-benefit to this, and I personally chose xyz".