Hacker News: hsaliak

New comment by hsaliak in "Autolith: A programming agent with a live runtime"

hsaliak — Sun, 23 Aug 2026 00:54:42 +0000

Ever since coding agents came out, It felt a little like we were implementing the self improving lisp programs of old.

This idea almost gets us there.

Could the next step be to make it the program itself?

New comment by hsaliak in "Malicious Rust crate Arrayref runs a build-time payload"

hsaliak — Thu, 20 Aug 2026 15:25:29 +0000

At least it’s safe

New comment by hsaliak in "The session you cannot take with you"

hsaliak — Fri, 31 Jul 2026 11:54:55 +0000

The state of Agent APIs is bad. completions API (supported indefinitely) but does not support reasoning. OpenAI's reasoning API started out well, but is moving in the direction as described well in the article. Anthropic's messages API is odd. It includes changes such as the recently introduced system messages that can be injected mid turn, but are not supported in all models (sonnet 5). So you are left with a pretty fragmented state. For coding agents, the practical move is to focus on getting it right with one API - eg reasoning, and let the router/provider handle the conversion for you.

Perhaps, there is value in having the de-facto API not be the Reasoning API from OpenAI but something from a neutral party?

Maybe a well defined open standard that facades over these APIs that can gain adoption. For that to happen, the party championing the API needs to have some reasonable traffic capture - OpenRouter perhaps, or a group of such routers coming together? While it wont solve the encrypted payload from the frontier lab problem, it will at least be a backstop in these APIs just becoming a back and forth of encrypted payloads over time.

New comment by hsaliak in "Agent Skill to Force Docs in ASD-STE100 Simplified Technical English"

hsaliak — Fri, 31 Jul 2026 02:32:08 +0000

yes it does - https://github.com/hsaliak/std_slop/blob/main/system_prompt....

I've added the same thing to the system prompt of the internal agent I wrote for work, which talks to claude models. I have not gone into the details on whether it adheres to the format exactly, but i do see visibly less slop and less marketing nonsense in the Assistant messages.

New comment by hsaliak in "Agent Skill to Force Docs in ASD-STE100 Simplified Technical English"

hsaliak — Thu, 30 Jul 2026 23:05:39 +0000

Seems to be doing too much, a 1 line in the system prompt is all you need. And it works well enough.

“Output tokens are precious, be succinct in your responses. Use ASD-STE100 simplified technical english”

New comment by hsaliak in "Our position on open-weights models"

hsaliak — Tue, 28 Jul 2026 03:40:49 +0000

Let all trust this team to deliver AGI.

New comment by hsaliak in "Where are YC founders now? OpenAI and Anthropic, mostly"

hsaliak — Thu, 16 Jul 2026 12:10:26 +0000

This graph biases outcomes (A| O) it would be interessting to have an others.. so we can view the whole picture

New comment by hsaliak in "Demis Hassabis has a plan to harness AI safely"

hsaliak — Tue, 14 Jul 2026 15:05:12 +0000

so the joke was the implication that they are not frontier.

New comment by hsaliak in "Demis Hassabis has a plan to harness AI safely"

hsaliak — Tue, 14 Jul 2026 14:59:50 +0000

no, this post was written by Demis from Deepmind.

New comment by hsaliak in "How do you use Vim in the era of AI?"

hsaliak — Fri, 10 Jul 2026 14:23:04 +0000

I have my own coding harness (std::slop), in that i focus on a vim centric flow. Basically a few commands open. up my $EDITOR which is vim.

1. /edit => opens in editor

2. /feedback => opens the last llm message in an editor so i can inline feedback. Think inline responses in email vs bottom posting.

3. /review => same as /feedback but opens up the diff so i do an inline review. Yes I still read the code it ships.

So basically in this flow vim becomes integral to doing anything involved.

New comment by hsaliak in "Better Models: Worse Tools"

hsaliak — Sun, 05 Jul 2026 02:11:14 +0000

It's been clear for some time that model tool calling is heavily fit to a few common patterns, it's unsurprising that a tool call that looks the same or has the same name, but works differently, is falling back to priors and causing problems.

Things are not quite AGI yet; which is why people are now saying that intelligence is the harness + model, because the harness makes up for limitations in generalization.

New comment by hsaliak in "Sakana Fugu"

hsaliak — Mon, 22 Jun 2026 08:42:28 +0000

so he's the quintessential brilliant jerk, ok

New comment by hsaliak in "John Jumper to join Anthropic"

hsaliak — Sat, 20 Jun 2026 08:44:50 +0000

Gemini fumbled not on the models but on the basics.

Gemini 3.1 flash was actually an amazing model to code with and their 20 dollar AI plans had solid value, but they locked it all behind 429s, needless gatekeeping of clients and poor product differentiation even among internal offerings. Users moved on. To claude for the best product, to OpenAI for the non gatekept API access. It’s hard to bring them back.

New comment by hsaliak in "If Claude Fable stops helping you, you'll never know"

hsaliak — Tue, 09 Jun 2026 23:20:29 +0000

Big Monsanto energy

New comment by hsaliak in "Anthropic's open-source framework for AI-powered vulnerability discovery"

hsaliak — Fri, 05 Jun 2026 00:56:40 +0000

I’ve been looking for a way to articulate this shift, and your analogy nails it. The value of libraries and infrastructure components in software engineering is eroding fast.

I am sure that in many organizations, teams responsible for this sort of work have less and less users coming to them.

New comment by hsaliak in "Backpressure is all you need"

hsaliak — Mon, 01 Jun 2026 02:20:39 +0000

I have a custom agent that generates patches like you will with kernel development and I review and merge those in. https://github.com/hsaliak/std_slop/blob/main/docs/mail_mode...

My agent forces this workflow by disabling modifications outside the coding step.

I added looping to this not too long ago. https://github.com/hsaliak/std_slop/blob/main/docs/mail-loop...

This gives me the best of both worlds, hand curated reviews and automation. I often get the best quality if I do both, with an agent doing a pass first.

New comment by hsaliak in "I'm going back to writing code by hand"

hsaliak — Mon, 11 May 2026 13:52:05 +0000

I wrote https://github.com/hsaliak/std_slop/blob/main/docs/mail_mode... to avoid the brain rot from just shooting slop. It has helped me stay sane, review code and make changes step by step.

I dont go as fast as with other agents, but this works for me, and I enjoy the process.

New comment by hsaliak in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

hsaliak — Sun, 10 May 2026 11:35:07 +0000

Its going to be interesting to see how this holds up in production after a release or two.

New comment by hsaliak in "Zig → Rust porting guide"

hsaliak — Tue, 05 May 2026 02:30:58 +0000

The problem with vibe coded re-writes is that you basically sign off on understanding the generated codebase at that point. Any historical knowledge of the codebase is gone.

New comment by hsaliak in "Specsmaxxing – On overcoming AI psychosis, and why I write specs in YAML"

hsaliak — Sun, 03 May 2026 11:48:58 +0000

the problem is not the forward pass, its the control/feedback loop when slop is written in response to the forward pass. Perhaps we should give the LLM 2 specs, one designed for the forward pass and another for the acceptance criteria /backward pass that's focused on tests, best practices and code, so that the output is independently verified?