Hacker News: vishvananda

New comment by vishvananda in "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"

vishvananda — Thu, 08 Oct 2026 21:20:17 +0000

The reason people aren’t freaking out is because most people are using heavily subsidized subscriptions.

I tried the cheapest provider on openrouter and burned through $50 in a few days. Quality was ok, seems slightly above Luna quality perhaps? But that $50 is 1/4 of my codex subscription where I could have burned that many tokens or more using Astra within my weekly reset.

This won’t last forever but as long as the frontier labs are subsidizing this heavily the open models won’t matter.

New comment by vishvananda in "What's the largest software project AI can complete on its own?"

vishvananda — Mon, 03 Aug 2026 18:01:37 +0000

I've been doing a lot of experimenting with this with a c++ compiler project[0]. I definitely experienced a lot of challenges, but I do believe it is possible to end-up in a consistent space by putting in some very careful guardrails. I covered some of the things i learned in the follow on blog posts. My more recent runs have been producing better code after continuing to improve harnesses, tests, and prompts. New blog post coming soon on v2 and v3 reruns. I'll be kicking off some v4 runs soon. Here is a teaser showing the later runs: https://storage.googleapis.com/ralph-run-viewer-zippy-960/in...

[0]: https://medium.com/@vishvananda/i-spent-2-billion-tokens-wri...

New comment by vishvananda in "Towards a harness that can do anything"

vishvananda — Wed, 15 Jul 2026 16:03:59 +0000

From harness? Because people expect a squishy set of things from a harness that is different from what I end up building. I end up with a rigid internal structure that the harness uses in-turn (tests with clear error messages, tools, etc.) and a matched rigid external structure that drives the turn tracking progress and deterministically handles the overall progress. You could call that whole thing a harness but that makes the definition muddy and hard to talk about. So scaffold or skeleton seems more appropriate. The harness constrains the agent. The matched endoskeleton and exoskeleton gives it structure.

New comment by vishvananda in "Towards a harness that can do anything"

vishvananda — Wed, 15 Jul 2026 15:37:13 +0000

I’m definitely on the deterministic code train as well. All of my success for long running tasks has been around wrapping the agentic harness (cc, codex-cli, etc.) in a deterministic workflow with deterministic gates. We need a name for this outer layer. In my mind that is the true harness because it constrains the agents failure mode. I think flow engineering has been proposed. Maybe it’s the agentic exoskeleton?

New comment by vishvananda in "Ask HN: What was your "oh shit" moment with GenAI?"

vishvananda — Fri, 05 Jun 2026 22:44:55 +0000

For me it was earlier this year when I started dusting off some old stalled projects and had an agent work on them. In a few days I:

* Built a clone of the Alpha Zero implementation[1] my team built at oracle

* Ported my hobby NES emulator from javascript to rust[2] (this actually took less than 30 minutes and worked on the first try)

* Implemented all of the lessons from the C++ Grandmasters Challenge (which eventually led to a complete c++ compiler[3])

The thing that flipped the switch was using it to build things that I actually put sweat-equity in to previously. I knew how hard these things were to build, so it landed in a way that other projects had not.

[1]: https://medium.com/oracledevs/lessons-from-implementing-alph...

[2]: https://github.com/vishvananda/popeye

[3]: https://medium.com/@vishvananda/i-spent-2-billion-tokens-wri...

New comment by vishvananda in "Constraint Decay: The Fragility of LLM Agents in Back End Code Generation"

vishvananda — Sun, 24 May 2026 17:20:15 +0000

I've been experimenting quite a bit with long-horizion agentic coding[1] and I have also noticed that agents seem to perform worse when forced into certain architectural patterns. I have found that is a bit better when including the constraints along the way instead of adding them after the fact. There seems to be a side-effect I have been calling "calcification", where a pattern starts appearing in the codebase and the agent follows the pattern to the point where it dominates the context and becomes self-reinforcing. This could potentially be a strength or a weakness for existing code bases depending the codebase quality. I will have more insights on this soon as more from-scratch runs conclude that include architectural guidance from the beginning.

[1]: https://medium.com/@vishvananda/i-spent-2-billion-tokens-wri...

New comment by vishvananda in "Agents need control flow, not more prompts"

vishvananda — Thu, 07 May 2026 19:17:02 +0000

I think there is a flow in most organizations from:

llm -> prompt -> result

llm -> prompt + prompt encoded as skill -> result

llm -> prompt + deterministic code encoded as skill -> result

I do think prompting to generate code early can shortcut that path to deterministic code, but we're still essentially embedding deterministic code in a non-deterministic wrapper. There is a missing layer of determinism in many cases that actually make long-horizon tasks successful. We need deterministic code outside the non-deterministic boundary via an agentic loop or framework. This puts us in a place where the non-deterministic decision making is sandwiched in between layers of determinism:

deterministic agentic flows -> non-deterministic decision making -> deterministic tools

This has been a very powerful pattern in my experiments and it gets even stronger when the agents are building their own determinism via tools like auto-researcher.

New comment by vishvananda in "The future of version control"

vishvananda — Sun, 22 Mar 2026 16:48:07 +0000

This is actually a very interesting moment to potentially overcome network effects, because more and more code is going to be written by agents. If a crdt approach is measurably better for merging by agent swarms then there is incentive to make the switch. It also much easier to get an agent to change its workflow than a human. The only tricky part is how much git usage is in the training set so some careful thought would need to be given to create a compatibility layer in the tooling to help agents along.

New comment by vishvananda in "I'm worried it might get bad"

vishvananda — Wed, 13 Aug 2025 15:03:49 +0000

I share the concern based on the current productivity expectations but I did stumble across something recently which makes me feel a lot better. There was a change in the tax code that coincides with the beginning of the post-pandemic layoffs[1]. This was changed back last month by the BBB which likely means a bunch of new R&D spend for big tech. I think this is why we are seeing intense M&A activity and if we can keep the AI hype under control it will probably lead to new hiring as well.

[1]: https://qz.com/tech-layoffs-tax-code-trump-section-174-micro...

New comment by vishvananda in "Nobody knows how to build with AI yet"

vishvananda — Sun, 20 Jul 2025 00:07:14 +0000

I am by no means an AI skeptic. It is possible to encode all sorts of things into instructions, but I don’t think the future of programming is every individual constructing and managing artisan prompts. There are surely some new paradigms to be discovered here. A code locking interface seems like an interesting one to explore. I’m sure there are others.

New comment by vishvananda in "Nobody knows how to build with AI yet"

vishvananda — Sat, 19 Jul 2025 19:07:51 +0000

I'm really baffled why the coding interfaces have not implemented a locking feature for some code. It seems like an obvious feature to be able to select a section of your code and tell the agent not to modify it. This could remove a whole class of problems where the agent tries to change tests to match the code or removes key functionality.

One could even imagine going a step further and having a confidence level associated with different parts of the code, that would help the LLM concentrate changes on the areas that you're less sure about.

New comment by vishvananda in "Updating Twelve-Factor: A Call for Participation"

vishvananda — Thu, 29 Aug 2024 17:02:44 +0000

Heroku is turning the 12 factor manifesto into a community project and modernizing it. I posted my thoughts in a blog[1], and I'd love to hear what other people think!

[1] https://medium.com/@vishvananda/the-rebirth-of-twelve-factor...

Updating Twelve-Factor: A Call for Participation

vishvananda — Thu, 29 Aug 2024 17:02:43 +0000

Article URL: https://blog.heroku.com/updating-twelve-factor-call-for-participation

Comments URL: https://news.ycombinator.com/item?id=41392955

Points: 11

# Comments: 2

New comment by vishvananda in "Show HN: Cursor AI Rules Directory (Open Source)"

vishvananda — Sun, 25 Aug 2024 14:17:13 +0000

This is something I’ve been arguing for for a while[1]. I called it a “Framework Knowledge Base”. I think it needs to go a bit further and include specific code examples, especially for newer bits that are not in the training set. Ultimately RAG or even fine tuning might be better than a system prompt. [1]: https://devops.com/the-rise-of-coding-assistants-superchargi...

New comment by vishvananda in "Show HN: Dotenv, if it is a Unix utility"

vishvananda — Mon, 29 Apr 2024 03:17:40 +0000

Doesn’t this already exist as https://www.npmjs.com/package/dotenv-cli ?

New comment by vishvananda in "[dead]"

vishvananda — Wed, 09 Aug 2023 17:16:57 +0000

I've followed Caleb on YouTube for a while, due to his MtG content. He is PhD in Optical Sciences that makes some very interesting AI art. He has created a new card game with hand curated AI art and some interesting rules aimed at solving a bunch of the problems around existing collectible card games. He wrote an essay[1] about his design goals which is fascinating. [1] https://calebgannon.com/2023/07/08/the-making-of-algomancy/

New comment by vishvananda in "Overhead of Python asyncio tasks"

vishvananda — Wed, 08 Mar 2023 22:10:13 +0000

Just reran the benchmarks from 10 years ago, python is only 37X slower than C on the benchmark now, and the go version is running faster than the C version. Python still has big productivity wins of course...

New comment by vishvananda in "Overhead of Python asyncio tasks"

vishvananda — Wed, 08 Mar 2023 21:44:39 +0000

Python is extremely slow for some tasks. I was surprised to discover how slow when I ran some benchmarks, despite having used python for many years at the time. It has been improving lately, but here is a blog post I made on the topic quite a few years ago that has some interesting comparisons: https://gist.github.com/vishvananda/7a2f1942d0e9ffff4093

New comment by vishvananda in "Progrium Technology Thesis"

vishvananda — Fri, 01 Apr 2022 17:05:38 +0000

This is definitely an intriguing line of thinking. I too am constantly appalled by the complexity we introduce into the things we build, but I suspect a lot of it has to do with human issues that can't be solved by better technology. That said, I'm very curious to see what tractor ends up looking like.

Progrium Technology Thesis

vishvananda — Fri, 01 Apr 2022 17:01:53 +0000

Article URL: https://progrium.com/blog/progrium-technology-thesis/

Comments URL: https://news.ycombinator.com/item?id=30880501

Points: 2

# Comments: 1