Hacker News: ekaesmem

New comment by ekaesmem in "Turn your best AI prompts into one-click tools in Chrome"

ekaesmem — Wed, 15 Apr 2026 07:07:09 +0000

So you're telling me we spent over a decade turning the browser from a sieve full of vulnerabilities into an impenetrable sandbox, and now we're directly introducing an APT?

Latent-Space Communication in Heterogeneous Multi-Agent Systems

ekaesmem — Sun, 01 Mar 2026 07:55:00 +0000

Article URL: https://arxiv.org/abs/2602.15382

Comments URL: https://news.ycombinator.com/item?id=47204654

Points: 7

# Comments: 1

FARS (Fully Automated Research System)

ekaesmem — Fri, 13 Feb 2026 08:34:21 +0000

Article URL: https://analemma.ai/blog/introducing-fars/

Comments URL: https://news.ycombinator.com/item?id=47000394

Points: 2

# Comments: 0

A Claude Code skill that gives the AI a "therapy session" when it gets stuck

ekaesmem — Fri, 13 Feb 2026 07:18:52 +0000

Article URL: https://github.com/zeahoo/hugme

Comments URL: https://news.ycombinator.com/item?id=46999868

Points: 1

# Comments: 0

New comment by ekaesmem in "GPT-5.3-Codex being routed to GPT-5.2"

ekaesmem — Wed, 11 Feb 2026 04:36:21 +0000

Update: I can access gpt-5.3-codex now. According to Alexander Embiricos, 9% of users were affected by over flagging over a period of 3 hours.

New comment by ekaesmem in "GPT-5.3-Codex being routed to GPT-5.2"

ekaesmem — Wed, 11 Feb 2026 00:09:53 +0000

Today I also discovered that the speed of gpt-5.3-codex in Codex CLI is extremely slow, and then I found that response.model was routed back to gpt-5.2-2025-12-11 by the upstream.

New comment by ekaesmem in "[dead]"

ekaesmem — Tue, 10 Feb 2026 03:30:16 +0000

Please use the "Show HN" tag.

New comment by ekaesmem in "Claude Code for Infrastructure"

ekaesmem — Wed, 04 Feb 2026 20:20:39 +0000

Please at least write the README.md by yourself. It's excessively lengthy.

DeepSeek Unveils Update to R1 Model

ekaesmem — Wed, 28 May 2025 16:49:14 +0000

Article URL: https://www.bloomberg.com/news/articles/2025-05-28/deepseek-unveils-update-to-r1-model-as-ai-race-heats-up

Comments URL: https://news.ycombinator.com/item?id=44117974

Points: 4

# Comments: 1

New comment by ekaesmem in "Show HN: DoubleMemory – more efficient local-first read-it-later app"

ekaesmem — Sun, 25 May 2025 05:39:49 +0000

Do you have plans to support an extension ecosystem, such as exporting content to Obsidian or other PKM apps?

New comment by ekaesmem in "Ask HN: What are you working on? (March 2025)"

ekaesmem — Sun, 30 Mar 2025 23:17:27 +0000

I just submitted a TinyML paper last night, focusing on creating a reproducible pipeline for model selection, compression, and deployment on constrained devices. I hope it gets accepted!

New comment by ekaesmem in "Show HN: Cursor IDE now remembers your coding prefs using MCP"

ekaesmem — Sat, 29 Mar 2025 01:14:37 +0000

The concept is promising, but I tested it and found the performance quite poor. I used one of my Python projects for the test, which consists of about 10k lines of Python code. The model I utilized was Claude 3.7 Sonnet with thinking.

in the first conversation round, I asked Claude to grasp the overall project and initialize its memory. Unfortunately, Claude experienced a hallucination and generated an episode that included a full name entirely unrelated to my project's actual full name, as my project name is an abbreviation.

In the second conversation round, I provided Claude with the full name of my project and requested it to correct its memory. In response, Claude apologized and claimed that it now understood the full name of my project, but it did not utilize any MCP command.

In the third conversation round, I specifically asked it to use the MCP command to update its memory. Claude successfully added a new episode but failed to remove the incorrect old episode.

It wasn't until the fourth conversation round that I directly pointed out that it should eliminate the incorrect old episode, and Claude finally completed the memory initialization that should have been accomplished at the end of the first round.

I have set up the correct Cursor Rules according to the README.

At this point, it appears this project is challenging to use with natural language. I need to explicitly instruct Claude on which specific tools to call for various operations to achieve the intended outcome.

Am I doing something wrong?