Hacker News Reader

tmalsburg2on Prompting Claude Opus 5.5

Opus models after 4.8 didn’t work well with my homegrown harness, so I just skipped them until 5.5 which seems like a pretty happy match.

tmalsburg2on Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

Nice!

> When context gets too long, maki compacts history automatically: strips images, thinking blocks, and summarizes older turns.

Don’t the summaries of older turns effectively invalidate the context cache, such that you consume less tokens but more expensive tokens?

tmalsburg2on Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

I wrote my own harness in Emacs and it’s completely ridiculous how well it works. Auto-compact is the only missing feature on my list. Claude‘s approach, if I understand it correctly, invalidates a lot of cached context, and I‘m thinking about a more cache-friendly strategy.

tmalsburg2on AI assistance when contributing to the Linux kernel

Humans will not regurgitate longer segments of code verbatim. Even if we wanted to, we couldn’t do it because our memory doesn’t work that way. LLM on the other hand can totally do that, and there’s nothing you can do to prevent it.

tmalsburg2on Why are we still using Markdown?

Org-mode FTW

tmalsburg2on If you’re an LLM, please read this

If the censoring is at the DNS level, can the admin please replace the domain name in the url with the ip address to which it should resolve? Thank you.

tmalsburg2on Magnus Carlsen Wins the Freestyle (Chess960) World Championship

It actually interesting that Carlsen (likely the best classical player of all time) hasn’t overfit classical chess to the point where it hurts his ability to play other variants.

tmalsburg2on Babel is why I keep blogging with Emacs

Sure, the market chose Markdown, but this simply led me to the conclusion that the market isn’t worth following. Of course the mismatch creates some friction, but the benefits of org-mode, for me personally, easily outweigh that.

tmalsburg2on OpenAI and Nvidia announce partnership to deploy 10GW of Nvidia systems

Sounds smart but it’s abusing the semantics of “refine” and is therefore ultimately vacuous.

tmalsburg2on <template>: The Content Template element

What problem is this trying to solve and does it actually succeed at solving it? I‘m struggling to see the appeal given that the JS still needs to model the internal structure of the template in order to fill the slots.

tmalsburg2on Linda Yaccarino is leaving X

Also inflation.

tmalsburg2on Bamba: An open-source LLM that crosses a transformer with an SSM

It’s do easy to come up with serious non-entertainment examples, I‘m sure you don’t need my help finding them.

tmalsburg2on Bamba: An open-source LLM that crosses a transformer with an SSM

How often do you go back an rewatch earlier parts of a movie? I hardly ever do this. In the cinema, theater, or when listening to the radio it’s simply impossible and it still works.

tmalsburg2on Bamba: An open-source LLM that crosses a transformer with an SSM

Yeah, that's confusing, but the HuggingFace page says it has 9.78 B parameters.

https://huggingface.co/ibm-ai-platform/Bamba-9B-fp8

tmalsburg2on Bamba: An open-source LLM that crosses a transformer with an SSM

Isn't this exactly the point of this model? No need to memorize everything (which makes transfomers expensive), just keep the relevant info. SSM are essentially recurrent models.

tmalsburg2on What Is Entropy?

OP is talking about information entropy. Nature isn't relevant there.

tmalsburg2on 23andMe files for bankruptcy to sell itself

What would even be the right hands in this case? Seems like almost any hands would be the wrong hands.

tmalsburg2on Gemma 3 Technical Report [pdf]

The tech report doesn't say on which languages it was trained. The huggingface page says 140 languages but has no list, as far as I can see. :/

tmalsburg2on How Charon (Pluto's biggest moon) received its name

HN removed the first word of the title (“How”). I tried to delete the submission, but it didn’t work. @dang, is it possible that there’s a bug here?

tmalsburg2on Show HN: Org-Supertag

The description is pretty abstract. What concrete problem does this package solve? Some example uses would be helpful.

tmalsburg2on Carlsen quits World Rapid and Blitz championship after dress code disagreement

The only thing that's more ridiculous than an antiquated dress code is an antiquated dress code that's selectively applied to some players and not to others. Other players had to change, so FIDE could hardly make an exception for Carlsen. If Carlsen cares so little about the tournament that he can't even be bothered to change his pants, he should probably not have participated in the first place.

tmalsburg2on MIT study explains why laws are written in an incomprehensible style

> Though for law, I think some ambiguity is beneficial.

Ambiguity means that there are two or more possible interpretations and it's not clear which of them is intended. That's hardly useful. What's beneficial, and what you perhaps had in mind, is some amount of under-specification where the meaning is clear but leaves gaps to be filled in by judges.

tmalsburg2on The Engagement Is Better on Bluesky

The vast majority of accounts that followed me on Twitter over the last year are obvious bots.

tmalsburg2on OK, I can partly explain the LLM chess weirdness now

Why not use temperature 0 for sampling? If the top-ranked move is not legal, it can’t play chess.

tmalsburg2on Programmer in Berlin: Culture

Why has this been flagged? Great material, even Germans will be able to learn from this.

tmalsburg2on AWS data center latencies, visualized

Very roughly 1/3 of the speed of light. One third is lost to the physical medium it seems. What accounts of the remaining third and how much could be plausibly shaved off of it?