Hacker News: dennisy

New comment by dennisy in "Show HN: Watch a neural net learn to play Snake"

dennisy — Sat, 16 May 2026 12:02:39 +0000

Very cool! Not GitHub repo?

I have started a new startup

dennisy — Wed, 13 May 2026 15:08:14 +0000

Article URL: https://dennisy.me/notes/i-have-finally-started-a-new-startup

Comments URL: https://news.ycombinator.com/item?id=48122931

Points: 1

# Comments: 0

New comment by dennisy in "Show HN: TikTok but for scientific papers"

dennisy — Mon, 11 May 2026 18:07:45 +0000

I love this and wanted to build this - but https://www.alphaxiv.org/ already exists, and it gets no social action (hardly any papers have comments), so this makes me doubtful about this.

I am interested to hear if anyone knows why the format may not resonate with researchers or those reading papers in general?

My own reason is that to get value from a "social" site the number of interactions has to be high and of a fast speed for people to continue to engage, which is maybe not possible to hit on research papers.

New comment by dennisy in "Show HN: GETadb.com – every GET request creates a DB"

dennisy — Fri, 08 May 2026 20:04:43 +0000

This is very cool!

But why do we need this? An agent can just have a local DB using SQLite for example.

Ask HN: Which memory systems are you using in your agents?

dennisy — Fri, 08 May 2026 13:01:44 +0000

Are you using an open source version, hosted product or maybe you have rolled your own?

What is working, what is missing, and how are you evaluating the usefulness of memory for your agentic projects?

Comments URL: https://news.ycombinator.com/item?id=48062468

Points: 5

# Comments: 0

New comment by dennisy in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

dennisy — Sat, 25 Apr 2026 09:38:50 +0000

This is a fair question, but not one I feel we can let people self answer.

I doubt many people will honestly admit they did no design, testing and that they believe the code is sub par.

It does give me an idea that maybe we need a third party system which can try and answer some of the questions you are asking… of course it too would be LLM driven and quite subjective.

New comment by dennisy in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

dennisy — Sat, 25 Apr 2026 07:45:15 +0000

True! But this is a very naive implementation, a proper implementation could surpass these challenges.

New comment by dennisy in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

dennisy — Sat, 25 Apr 2026 07:06:53 +0000

Congratulations on the launch!

There is lots of competition in this space, how is your tool different?

New comment by dennisy in "Workspace Agents in ChatGPT"

dennisy — Sat, 25 Apr 2026 07:01:49 +0000

I think this used to be the trick, but now with AI it is such a general purpose technology I am not sure that makes sense. Users can “niche down” in a generic app, using prompts and configs.

New comment by dennisy in "Show HN: Broccoli, one shot coding agent on the cloud"

dennisy — Wed, 22 Apr 2026 20:19:50 +0000

Fair play for launching this, it looks like a neat project.

However I feel it will be an uphill battle competing with OpenAI and Anthropic, I doubt your harness can be better since they see so much traffic through theirs.

So this is for those who care about the harness running on their own infra? Not sure why anyone would since the LLM call means you are sending your code to the lab anyway.

Sorry I don’t want to sound negative, I am just trying to understand the market for this.

Good luck!

New comment by dennisy in "Workspace Agents in ChatGPT"

dennisy — Wed, 22 Apr 2026 20:11:34 +0000

I feel for the startups sweating each one of these frontier lab releases.

How many more are thinking “am I next?”

New comment by dennisy in "Vercel April 2026 security incident"

dennisy — Sun, 19 Apr 2026 19:24:23 +0000

So what are you suggesting do not allow companies to sell such tools?

New comment by dennisy in "Vercel Says Internal Systems Hit in Breach"

dennisy — Sun, 19 Apr 2026 17:59:52 +0000

Ohh this is very cool!

New comment by dennisy in "Vercel April 2026 security incident"

dennisy — Sun, 19 Apr 2026 17:55:41 +0000

I think most people would agree.

However it is less clear on how to do this, people mostly take the easiest path.

New comment by dennisy in "Cirrus Labs to join OpenAI"

dennisy — Sat, 11 Apr 2026 19:41:00 +0000

That is good advice!

I am too late for that as I am full time but also lucky to have had a previous exit.

I am planning to go the VC route this time, because the problem I am going after feels VC size.

However I feel bootstrap or small F&F round gives you more flexibility when it comes to exits.

Congrats again!

New comment by dennisy in "Cirrus Labs to join OpenAI"

dennisy — Sat, 11 Apr 2026 15:27:01 +0000

Congratulations!

Can you talk a bit more about your journey without raising funds?

Also what does HN think of that path today when trying to launch a new AI startup?

New comment by dennisy in "Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs"

dennisy — Sat, 11 Apr 2026 15:23:42 +0000

I was thinking something that runs in the same process, and does not require docker or a third party API.

For example Monty by the pydantic team, or the Anthropic sandbox which I believe uses OS level primitives.

New comment by dennisy in "Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs"

dennisy — Fri, 10 Apr 2026 19:55:55 +0000

Congrats on the launch, the agentbox-sdk looks interesting, but seeing as the first commit was 3 days ago - I feel a little wary to use it just yet!

One question, do you have plans for any other forms of sandboxing that are a little more "lightweight"?

Also how do you add more agent types, do you support just ACP?

New comment by dennisy in "Claude Managed Agents"

dennisy — Wed, 08 Apr 2026 19:32:05 +0000

Let’s just shorten it to AaS?

New comment by dennisy in "LLM Wiki – example of an "idea file""

dennisy — Sun, 05 Apr 2026 13:11:39 +0000

The “next gen of models” argument is a valid one and one I think of often, but if you truly buy it, it would stop do creating anything - since the next gen of models could make it obsolete.