HNHacker News
TopNewBestAskShowJobs

dennisy

614 karma · joined October 31, 2016

meet.hn/city/gb-London

Socials: - github.com/ydennisy - linkedin.com/in/dennisyurkevich - x.com/ydennisy_

Interests: AI/ML, Data Science, DevOps, Entrepreneurship, Programming, Startups, Web Development

---

submissionscomments
dennisy··on Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs
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?

dennisy··on Claude Managed Agents
Let’s just shorten it to AaS?
dennisy··on LLM Wiki – example of an "idea file"
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.
dennisy··on Tell HN: Your AI startup is a Next.js page, OpenAI_API_KEY, & Stripe invoice
Spicy! Upvoted just because I would look forward to the HN debate that would happen on this topic!

My personal view here has shifts quite often, yes software is getting easier to build at an alarming rate, but designing good software is not (yet), and new novel software is not in the training set so should remain hard to build, forever (?)

To address the main comment, yes lots of apps are just wrappers, and I feel this is not sustainable, we will not need all these specialised apps since AI is such a general interface to computing.

dennisy··on MemEvolve: Meta-Evolution of Agent Memory Systems
Just came across this and found it to be quite interesting - they propose to evolve the memory architecture per task, which seems like a nice idea since it is so hard to know up front what your agent needs to learn / remember.

It reminds me of GEPA & Textgrad.

Would love to hear if anyone has worked on anything of this sort in practice.

dennisy··on Marketing for Founders
How did you guess it was AI slop? I read it and answered before seeing your comment :)
dennisy··on Marketing for Founders
Whilst this is a very valid view, I am not sure there is evidence for it, if you have it please do provide it.

It is not obvious to me that one credible citation is better than having appeared many times in the training data.

Also knowledge releases of models are too slow to be depended on for marketing in my view. It is the search / retrieval of LLMs for which one can optimise.

A final point would be that none of this changes the point made, which is that there too much noise due to too many products being shipped.

dennisy··on Data Activation Thoughts
Could you please expand on “none of them find the tools very useful”?

I would love to know how big your sample is, in what way the tools fail, what features are missing etc.

dennisy··on Hashcards: A plain-text spaced repetition system
I have thought about this idea many times and think it would be amazing!

Also could think of it a little like a “Wikipedia of flashcards”.

Would you be interested in working on something like this?

dennisy··on Training LLMs for honesty via confessions
Are we only able to think of these systems as some form of human and probe them from the outside like a therapist?

Surely these sorts of problems must be worked upon from a mathematical standpoint.

dennisy··on Show HN: tomcp.org – Turn any URL into an MCP server
I am not quite clear why this adds value over a simple web fetch tool which does not require configuration per site.
dennisy··on What if you don't need MCP at all?
This is incredibly simple and neat! Love it!

Will have a think about how this can extended to other types of uses.

I have personally been trying to replace all tools/MCPs with a single “write code” tool which is a bit harder to get to work reliably in large projects.

dennisy··on Modular monolith and microservices: Modularity is what matters
The suggested “_contracts” folder lives at the top level of the modules or inside each feature/module?

My guess is it’s a top level folder which shows the cross module deps.

dennisy··on Toolkit to help you get started with Spec-Driven Development
This is a great read and one which for me personally really summarises my feeling on developing with LLMs.
dennisy··on Toolkit to help you get started with Spec-Driven Development
Tern looks very interesting.

On your homepage there is a mention that Tern “writes its own tools”, could you give an example on how this works?

dennisy··on Learning from failure to tackle hard problems
Is this related to the article?
dennisy··on Codemaps: Understand Code, Before You Vibe It
Looks an interesting enough feature to give Windsurf a try!
dennisy··on Deepnote, a Jupyter alternative, is going open source
100%, you can feel this is GPT5 style.
dennisy··on Pomelli
Lots of startups are launching in this space. Creating ad copy and assets is obviously a hot idea.

I would love to hear what people’s takes on the market dynamics are, especially if any of the YC founders working in this space see this!

dennisy··on Pomelli
Yeah, I was thinking the same. Quite a few YC companies are going after this.

What sort of market dynamics do people predict here, winner takes all? Especially when this is integrated into the platforms of distribution.

dennisy··on Show HN: Synnote – AI That Turns Notes into Action
This looks cool, but I am not sure what other Todos the AI component would be able to handle apart from doing research on notes?

Also having AI write notes is really missing the point of writing notes in my opinion.

dennisy··on The Programmer Identity Crisis
I absolutely loved this piece.

I also agree with comments on this thread stating that problem solving should be the focus and not the code.

However my view is that our ability to solve problems which require a specific type of deep thought will diminish over time as we allow for AI to do more of this type of thinking.

Purely asking for a feature is not “problem solving”.

dennisy··on Show HN: I built an MCP server using Cloudflare's code mode pattern
Whilst I agree that Cloudflare have a vested interest here, there have been other proposers of this concept such as huggingface.

https://huggingface.co/blog/smolagents

dennisy··on Launch HN: Trigger.dev (YC W23) – Open-source platform to build reliable AI apps
What a breath of fresh air! Love this comment!
dennisy··on Launch HN: Trigger.dev (YC W23) – Open-source platform to build reliable AI apps
The platform looks great!

However I do personally really dislike that everyone is either marketing themselves or has truly pivoted to AI agents…

This seems like a great platform to run any type of tasks.

dennisy··on Next.js is infuriating
Do people feel this way about Nuxt too? They have recently joined Vercel…
dennisy··on An LLM is a lossy encyclopedia
Not sure this is a novel perspective, yet the author in his normal style claims he has discovered the atom.
dennisy··on Cognitive load is what matters
Whilst I agree with lots of ideas in this piece, I fell out of love with it when clicking into the discussion on what should be done instead of using a layered architecture.

The author makes valid points but they are vacuous and do not provide concrete alternatives.

Many engineering articles disappoint me in this way, I get hyped by all the “don’t dos”, but the “do dos” never come.

dennisy··on Show HN: Stagewise – frontend coding agent for real codebases
I really liked the look of the product, but since the founder replied multiple times to questions / comments some thing along the lines of “we have not really spent time on…” comes across not very well thought out!

However I am personally looking for a product exactly like this! I really want LLMs to make beautiful UI for me.

dennisy··on Good system design
This post has some good concepts, but I do not feel it helps you design good systems. It iterates options and primitives, but good design is when and how you apply them, which the post does not provide.
← PreviousPage 2 of 9Next →