Earendil
earendil.com · Personal blog · on HN since 2026
Earendil's site hosts posts on the Pi coding agent, covering prompt caching, compaction, harnesses, and session portability across LLM providers.
What HN saysHN commenters link it for Pi, praised for minimal context overhead, fewer tools, and a small system prompt, and for its session portability post.
18HN people shared it
9linked it in comments
13stories submitted
22story points
2 months agolast shared
2026people per year2026
Most-shared posts
- 1The Session You Cannot Take with You5 people · 6 points · first shared 2026 · 1 comments on HN
- 2Prompt Caching in Agents5 people · 5 points · first shared 2026 · discussion on HN
- 3Pi's Minimalism Is Its Advantage2 people · 4 points · first shared 2026 · discussion on HN
- 4How Compaction Works in Pi2 people · 3 points · first shared 2026 · discussion on HN
- 5Pi Agent Being Merged?2 people · 2 points · first shared 2026 · discussion on HN
- 6What Is a Harness?1 people · 2 points · first shared 2026 · discussion on HN
- 7Purpose1 people · first shared 2026
- 8Announcing pi and lefos1 people · first shared 2026
- 9Homepage1 people · first shared 2026
What HN people wrote when they linked it
erk__ · 2026-01-12
tbh I think it is just a question about time before flask guy has something to sell: https://earendil.com/
jauntywundrkind · 2026-08-08
Like glm-5.x I think it has enormous self introspection that it often trips up on, but that this self reflection is actually a superpower, that enables incredibly good output. And from (in some cases) very small models.
If you watch it think, which you can, unlike American closed models, you can steer it. You can provide a a massive rocket ship stratospheric boost to help it orient itself. You have no self correction, there is no multiplayer in American proprietary models.
Sure it's great having super powerful mystic oracles that have the "right" answers. But I love respect & revere the open thinking. No it's not automous. But it is brilliant. And it considers. A lot. Deeply. It chases. That to me is the most human of models, even as it falls far astray.
You should help it. You can. Unlike these vicious dark surfaces which yield and tell you nothing. I think this is the actual meta-core-super-point of "The session you cannot take with you" (link below). It's the session that does not care about you, will not interact with you, will not peer with you, that is a dead remote far off oracle to you. Fuck these "oracles". They are a plague against the human spirit. We should alloy humanity and AI to Augment Intellect (Engelbart). (To do less is species treason.)
https://earendil.com/posts/session-portability/
https://news.ycombinator.com/item?id=49118781
apitman · 2026-08-06
As low as it is, switching between providers on OpenRouter is still lower.
That said, it's a fair point. For me, it boils down to things covered here: https://earendil.com/posts/session-portability/
Things like obscured reasoning traces.
tosh · 2026-08-04
Pi is pretty good actually
(it has way less context spam, fewer tools and smaller system prompt than the usual suspects)
databricks also looked at this: https://earendil.com/posts/pi-autoresearch-and-databricks/
msdz · 2026-08-03
Which is why big labs have been working hard on making their harness not be stateless any longer:
https://earendil.com/posts/session-portability/
“Just take the session thread to another provider” might not be feasible anymore soon-ish.
DavidHaerer · 2026-08-03
According to [1] there is - unfortunately - increasingly more state in LLM sessions.
1: https://earendil.com/posts/session-portability
the_mitsuhiko · 2026-07-31
Because if you don't, you trash the KV cache and things get way more expensive. We wrote about it here: https://earendil.com/posts/prompt-caching/
Encrypted reasoning content is one of the things we keep as blobs in the transcript, even though we can only send it back to the original provider that created them, as otherwise we cannot keep caches live.
easymuffin · 2026-07-14
Pi (Earendil) is afaik vc-backed. Accel, Balderton, etc see last section of https://earendil.com/posts/announcing-pi-and-lefos/
rkwtr1299 · 2026-03-21
And yet https://earendil.com/purpose/ is dabbling in AI and many posts by Ronacher are low key promoting AI.
He is contributing to the madness.