Hacker News: anentropic

New comment by anentropic in "Kimi K3: Open Frontier Intelligence"

anentropic — Thu, 16 Jul 2026 17:29:09 +0000

Quite impressed by the result to my first prompt...

How feasible is it to hook Kimi up to do GitHub code reviews? the Copilot quotas got really stingy recently

New comment by anentropic in "Show HN: Pylon Sync, an agent-first full-stack realtime framework"

anentropic — Fri, 10 Jul 2026 17:33:02 +0000

Did it occur to you that naming it "Pylon" makes it sound like a Python project...?

(Py- anything is usually Python in this industry)

New comment by anentropic in "ActivityPub over ATProto"

anentropic — Fri, 10 Jul 2026 17:01:44 +0000

There's not one server instance type, there are different components to it

To 'own your data' you just need a PDS, which should be cheaper to run than an ActivityPub server

To build an app you need some of the more expensive parts

New comment by anentropic in "Rewriting Bun in Rust"

anentropic — Thu, 09 Jul 2026 09:18:07 +0000

Those were in the article https://bun.com/blog/bun-in-rust#2-5-faster

New comment by anentropic in "Benchmarking coding agents on Databricks' multi-million line codebase"

anentropic — Thu, 09 Jul 2026 08:58:32 +0000

> the results showed clear clustering of the models and harnesses into 3 capability tiers

pretty sure the only thing making that 'clear' is the coloured stripes, if you took that away it'd look like two tiers

good result for GLM 5.2 though

and Sonnet 5 seems like a waste of time

New comment by anentropic in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

anentropic — Thu, 09 Jul 2026 08:52:47 +0000

It's not very clear on the website, couldn't find a list of models or quota/pricing per model anywhere

New comment by anentropic in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

anentropic — Thu, 09 Jul 2026 08:52:18 +0000

Oh, the free plan said "Slow" so I thought maybe the others had the fast version :)

New comment by anentropic in "NoiseLang: Where N = 5 is a Dirac delta"

anentropic — Wed, 08 Jul 2026 19:04:43 +0000

Beautiful

New comment by anentropic in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

anentropic — Wed, 08 Jul 2026 17:57:19 +0000

https://devin.ai/pricing

Apparently 'free' on the $20/mo Devin plan (presumably within some quota still)

and that is "via Cerebras at 1000 TPS" according to the announcement

I live on Opus 4.8 High and their benchmark scores SWE-1.7 slightly higher ... if at all realistic that sounds like a great deal ... too good to be true?

New comment by anentropic in "Every new car sold in the European Union must include a driver monitoring camera"

anentropic — Wed, 08 Jul 2026 11:30:37 +0000

best pronounced with a Yorkshire accent I believe

New comment by anentropic in "30papers.com – Ilya's 30 essential ML papers, in a beginner friendly format"

anentropic — Wed, 08 Jul 2026 11:25:58 +0000

Has anyone tried just asking John Carmack...?

New comment by anentropic in "Show HN: Margarita - Programming language for Agents using Markdown-ish syntax"

anentropic — Thu, 02 Jul 2026 14:13:17 +0000

I am puzzled by the example on the homepage - does it show the agent failing to follow the instructions properly?

> Review this code snippet and set `score` to a number from 0–10

> ↳ set score = 72

...or is it the comments further down influencing the behaviour:

    // This runs the agent
    // score is set to 72
    // feedback is set to Simple and correct...
    @effect run

if so is that supposed to happen?

it's all a bit confusing

New comment by anentropic in "Show HN: Kage, verification and freshness for Google's OKF agent memory"

anentropic — Wed, 01 Jul 2026 15:29:51 +0000

What is the intended team workflow with git?

I do some work on a PR, Kage generates some new memories - I commit those with the feature?

> Branch changes can be summarized with `kage propose --from-diff` and checked with kage pr check.

Is this suggested as a pre-commit hook type of activity?

Are there actions that should run periodically in CI, or upon merges to base branches?

New comment by anentropic in "GLM 5.2 beats Claude in our benchmarks"

anentropic — Mon, 29 Jun 2026 11:56:06 +0000

It's a nice technical achievement but looks unusably slow for actual work

New comment by anentropic in "Previewing GPT‑5.6 Sol: a next-generation model"

anentropic — Fri, 26 Jun 2026 18:55:10 +0000

Previewing : a next-generation model

New comment by anentropic in "Show HN: OpenKnowledge – open source AI-first alternative to Obsidian/Notion"

anentropic — Fri, 26 Jun 2026 09:16:33 +0000

I wish (in general, not a criticism of this project) there was some way for claude.ai to write to a version controlled KB, ie from chats in the mobile app

This is mostly a Claude problem

So far the closest thing to what I want is using Claude Code in the mobile app to work in some repo and tell it not to write code, just have a discussion, and then eventually ask it to write the md doc or whatever.

I can then add that GitHub repo to a claude.ai 'Project' files and chats within the project can see the contents, but can't write back to it unfortunately.

New comment by anentropic in "An entire Herculaneum scroll has been read for the first time"

anentropic — Fri, 26 Jun 2026 08:49:25 +0000

Just wonderful

Wonderful that all of this amazing technology exists

Wonderful that we used it to read these ancient scrolls

Thank you

New comment by anentropic in "Markdy: Like Mermaid Diagrams, but for Motion"

anentropic — Thu, 25 Jun 2026 13:35:58 +0000

Such a weird and creepy choice

New comment by anentropic in "Will It Mythos?"

anentropic — Tue, 23 Jun 2026 08:58:56 +0000

Exactly this. And it's not really possible to do repeatable trials, it's all just vibes. People have very little awareness of their own cognitive biases.

New comment by anentropic in "Ask HN: What are you working on? (June 2026)"

anentropic — Mon, 15 Jun 2026 15:00:45 +0000

Various stuff around Semantic Views for data warehouse / analytics

Starting with https://anentropic.github.io/duckdb-semantic-views/ which is basically a clone of Snowflake's semantic views but for DuckDB

(see also Databricks Metric Views)