hsaliak
hsaliak on Hacker News
A good % of the Google of yesterday is now in working in frontier labs, crushing it.
id' normally hate this but with agents this is awesome
Nobody is going to read that though, reading will go the way of code reviews. That’s the problem.
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?
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.
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.
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”
Let all trust this team to deliver AGI.
This graph biases outcomes (A| O) it would be interessting to have an others.. so we can view the whole picture
so the joke was the implication that they are not frontier.
no, this post was written by Demis from Deepmind.
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.
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.
so he's the quintessential brilliant jerk, ok
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.
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.
Its going to be interesting to see how this holds up in production after a release or two.
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.
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?
nobody knows what to build when everything can be built, there is no moat.
Using CRDT gossip to inform scaling is a clever idea. You are on to something there. Perhaps extract it as a core library/concept from the runtime? I feel that would be generally useful!
I have a coding agent
https://github.com/hsaliak/std_slop where the sessions are in SQL ledger. So /session [new, clone, deletes, undo] are supported and all sessions are persistent. Cloning lets you 'fork' the context and undo lets you roll back, basically solving the problem you state above.
Sessions are linear though, so you cant do this _while_ an existing session is cooking.
That said, I am excited about this update too, I've been playing with ACP support and Zed's UX was bare bones. I want to run my agent with multiple workers now, and see what happens.
I find parallel agents to be an exception rather than a norm. Maybe I’m the problem?
For those exceptional cases, opening a few more terminals gets the job done. It’s unclear to me if this needs to be the primary workflow. My brain naturally does better on deep work on one problem..
Clojure had lousy error messages, agents deal with this well.
Clojure is capable of producing some of the most dense code I’ve ever seen, so manual code reviews really start to feel like a bottleneck unless your goal is to level up.
I've long had the same idea.. this one has legs.