Hacker News: _jayhack_

New comment by _jayhack_ in "Memoirs of Extraordinary Popular Delusions and the Madness of Crowds (1852)"

_jayhack_ — Tue, 30 Jun 2026 15:26:04 +0000

The content on "priming" (significant pillar of the book) has collapsed as part of the reproducibility crisis in psychology. More here: https://replicationindex.com/2017/02/02/reconstruction-of-a-...

Ultracoding: The Next Frontier

_jayhack_ — Mon, 15 Jun 2026 23:53:18 +0000

Article URL: https://www.jay.ai/blog/ultracoding-the-next-frontier

Comments URL: https://news.ycombinator.com/item?id=48548746

Points: 3

# Comments: 0

New comment by _jayhack_ in "LLMs are not the black box you were promised"

_jayhack_ — Wed, 03 Jun 2026 16:12:40 +0000

Deep Learning is a Black Box and Here's Why You Should Use Random Forests Because They Are Interpretable

This was the mantra of applied machine learning c. 2010 - 2024 for anyone paying attention. No longer the case.

New comment by _jayhack_ in "LLMs are not the black box you were promised"

_jayhack_ — Wed, 03 Jun 2026 03:02:29 +0000

For some definitions of better, yes. Chinese is more token efficient for representing fixed text, for example, although this does not always lead to better performance on downstream tasks.

New comment by _jayhack_ in "LLMs are not the black box you were promised"

_jayhack_ — Wed, 03 Jun 2026 03:01:16 +0000

As the author - this was adapted from a thread posted on X in March (linked in article). AI did the adaptation, I wrote the original article. It seems like it inserted grammatically correct hyphens, otherwise the copy is mine.

New comment by _jayhack_ in "LLMs are not the black box you were promised"

_jayhack_ — Wed, 03 Jun 2026 03:00:05 +0000

Hello, I am the author - this is not an LLM-generated article, I wrote this by hand and had an LLM adapt it from a thread on X. You can see the original thread here: https://x.com/mathemagic1an/status/2035850046735098065

> the fact that language models have human-interpretable representations and neurons has been known since BERT... Circuits research also does not come from Anthropic... The article does not claim Anthropic invented the field, rather that they have had important contributions to it. This is intended as an overview into a specific set of ideas that are working for mechanistic interpretability. Not a formal literature review.

LLMs are not the black box you were promised

_jayhack_ — Tue, 02 Jun 2026 23:27:30 +0000

Article URL: https://www.jay.ai/blog/llms-are-not-a-black-box

Comments URL: https://news.ycombinator.com/item?id=48377631

Points: 56

# Comments: 41

New comment by _jayhack_ in "Launch HN: Freestyle – Sandboxes for Coding Agents"

_jayhack_ — Mon, 06 Apr 2026 17:10:10 +0000

Would love to understand how you compare to other providers like Modal, Daytona, Blaxel, E2B and Vercel. I think most other agent builders will have the same question. Can you provide a feature/performance comparison matrix to make this easier?

New comment by _jayhack_ in "Cameras and Lenses (2020)"

_jayhack_ — Thu, 01 Jan 2026 19:58:21 +0000

Great article. For another fantastic explainer on optics, see 3Blue1Brown's video on refraction: https://www.youtube.com/watch?v=KTzGBJPuJwM

New comment by _jayhack_ in "Codemaps: Understand Code, Before You Vibe It"

_jayhack_ — Tue, 04 Nov 2025 22:09:45 +0000

> static analysis tools that produce flowcharts and diagrams like this have existed since antiquity, and I'm not seeing any new real innovation other than "letting the LLM produce it".

Inherent limitation of static analysis-only visualization tools is lack of flexibility/judgement on what should and should not be surfaced in the final visualization.

The produced visualizations look like machine code themselves. Advantage of having LLMs produce code visualizations is the judgement/common sense on the resolution things should be presented at, so they are intuitive and useful.

New comment by _jayhack_ in "Meta Superintelligence Labs' first paper is about RAG"

_jayhack_ — Sun, 12 Oct 2025 00:09:24 +0000

Vector embedding is not an invention of the last decade. Featurization in ML goes back to the 60s - even deep learning-based featurization is decades old at a minimum. Like everything else in ML this became much more useful with data and compute scale

New comment by _jayhack_ in "Game over for pure LLMs. Even Rich Sutton has gotten off the bus"

_jayhack_ — Fri, 26 Sep 2025 22:25:52 +0000

Gary Marcus has been taking victory laps on this since mid-2023, nothing to see here. Patently obvious to all that there will be additional innovations on top of LLMs such as test-time compute, which nonetheless are structured around LLMs and complementary

New comment by _jayhack_ in "Show HN: Vibe Kanban – Kanban board to manage your AI coding agents"

_jayhack_ — Fri, 11 Jul 2025 15:52:31 +0000

Very cool and interesting project. Ideas like this are a threat to traditionally-conceived project management platforms like Linear; that being said, Linear and others (Monday, ClickUp, etc.) are pushing aggressively into UX built for human/AI collaboration. I guess the question is how quickly they can execute and how many novel features are required to properly bring AI into the human project workspace

New comment by _jayhack_ in "Measuring the Impact of AI on Experienced Open-Source Developer Productivity"

_jayhack_ — Thu, 10 Jul 2025 19:25:57 +0000

This does not take into account the fact that experienced developers working with AI have shifted into roles of management and triage, working on several tasks simultaneously.

Would be interesting (and in fact necessary to derive conclusions from this study) to see aggregate number of tasks completed per developer with AI augmentation. That is, if time per task has gone up by 20% but we clear 2x as many tasks, that is a pretty important caveat to the results published here

New comment by _jayhack_ in "Show HN: AI for Building Design, Planning, and Permitting"

_jayhack_ — Mon, 26 May 2025 23:03:47 +0000

It looks like you used AI-generated videos for customer testimonials. This should be illegal

New comment by _jayhack_ in "Type-constrained code generation with language models"

_jayhack_ — Wed, 14 May 2025 01:57:49 +0000

Also worth checking out MultiLSPy, effectively a python wrapper around multiple LSPs: https://github.com/microsoft/multilspy

Used in multiple similar publications, including "Guiding Language Models of Code with Global Context using Monitors" (https://arxiv.org/abs/2306.10763), which uses static analysis beyond the type system to filter out e.g. invalid variable names, invalid control flow etc.

Show HN: Codegen – SWE Agents for any repo

_jayhack_ — Fri, 18 Apr 2025 17:26:54 +0000

Hey folks, excited to launch Codegen: a platform for SWE agents.

Codegen lets you prompt agents to perform programming tasks across code, Github, Linear, Slack and more. Ask for impressively complex code modifications and watch it autonomously produce pull requests, respond to feedback, diagnose issues, run tests and more.

Try the following:

- "@codegen Can you add stripe checkout to my frontend?"

- "@codegen Who is the top contributor to my repo last week?"

- "@codegen Can you research and flesh out this Linear ticket?"

Codegen has full access to an isolated dev machine, ability to search the web, and is freakishly smart due to the incredible agentic capabilities of Claude 3.7.

This is based on the Claude Code architecture: a single-strand agent with tool use.

We also support an API (https://docs.codegen.com/introduction/api) for programmatically triggering agents. Rig them up to run as part of your CI, etc.

Give it a spin! Free to try at codegen.com.

Would love any feedback that folks are willing to provide!

Comments URL: https://news.ycombinator.com/item?id=43730097

Points: 2

# Comments: 0

New comment by _jayhack_ in "Launch HN: mrge.io (YC X25) – Cursor for code review"

_jayhack_ — Tue, 15 Apr 2025 15:12:09 +0000

If you are looking for an alternative that can also chat with you in Slack, create PRs, edit/create/search tickets and Linear, search the web and more, check out codegen.com

New comment by _jayhack_ in "Fintech founder charged with fraud; AI app found to be humans in the Philippines"

_jayhack_ — Fri, 11 Apr 2025 00:26:18 +0000

Related article from mid-pandemic: https://www.theinformation.com/articles/shaky-tech-and-cash-...

A friend asked me to do diligence on this company circa 2021 given my personal background in ML. The founder was adamant they had a "100% checkout success rate" based on AI, which was clearly false. He also had 2 other startups he was running concurrently (?)

Live and learn!

New comment by _jayhack_ in "Show HN: Codemcp – Claude Code for Claude Pro subscribers – ditch API bills"

_jayhack_ — Thu, 20 Mar 2025 01:31:13 +0000

Codegen is an MCP client that you can trigger via Slack: codegen.com