jeffnash

I agree the gap is narrowing quickly, especially with workflows in CC. For me, a few large advantages still remain:

1/ Allowing me to easily plug in any harness, using any provider, and make it a first-class worker. Omnigent has out of the box ACP support and it's trivial to use that to add first-class support for any harness out there. I love the ability to have CC + Opus plan, Codex + Luna implement, Pi + Qwen 3.8 give a tie-breaking opinion on a design decision that Opus flagged and Grok and Codex couldn't agree on, all orchestrated by a model of my choosing from any provider using Omnigent's main agent harness.

2/ Reusable agent systems rather than just reusable workflows. You can define agents in YAML whose subagents embody particular roles, with different models/harnesses, skills, plugins, tools, etc. preconfigured for each one.

Of course, claude workflows are now durable but Omnigent's agnt definitions are a bit more abstract in that they define the subagents that are available and how they should work by default rather than the workflow itself (i.e. the specific JTBD). If I have a common workflow that consists of, for example, Sol + Codex writing some script to scrape some data, Pi + a cheap DeepSeek-tier model formatting that data en masse, then Fable + CC doing some advanced analysis on it, I can embody that with a yaml agent definition that I can then use to run with my task of the day as a prompt. All of this is orchestrated by a model of my choice using Omnigent's harness.

This might look like: 'smart scraping agent with all sorts of scraping skills and tools pre-loaded', a 'bulk data processing agent with a cheap, fast model and plenty of pandas/numpy skills preloaded', and 'frontier model to interpret and reason on the implications of the processed data'. The main agent would have instructions about the general workflow of such tasks and when to invoke and delegate tasks to which subagent. The definition describes the workers available to the orchestrator and how they should generally behave, rather than hard-coding the workflow itself. I love that I can create those definitions and re-use them.

All that said, I am sure the labs will come up with their own similar products to (2) (e.g. dots today). I also recently noticed that Claude Code now has subagent 'teams' rather than just 'general-purpose'/'explore' subagents, and these seem to be longer-lived. This seems to be encroaching on the agent yaml definitions, albeit with less fine-grained control on my end. Therefore, the tl;dr (for me at least) is vendor neutrality; I don't think we'll ever see a product coming out of a frontier lab that eagerly delegates a task to their competitor's model (and bank account).

Reminds me a lot of omnigent (which I am a huge fan of) with a persistent memory layer. Unlike omnigent's subagent threads, the DAG it uses to coordinate other harnesses doesn't look to be durable; I am curious as to whether this is by design or is a forthcoming feature, as this essentially makes or breaks my use case of long-running project-sized implementation sessions.

In any event, it's great to see competition in this meta-harness space, which is likely one that none of the frontier labs will touch since it, by definition, would utilize their competitors' products.

Sorry about that, I accidentally a word (hope that reference doesn't date me)

I fear the opposite will happen. Guy driving like a maniac almost side-swipes you in traffic? "Look at this 1-bit quantized Qwen 2.5 7B over here".

out of curiosity, what type of code/language do you usually use flash to write?

I'm actually interested to see how the token discount maps to the usage limit consumption. The conspiracy theorist in me wonders if they're making up the discount and resultant load increase on the API end by reducing effective usage on the subscription end.

I realized I missed a few words here: I meant "especially when you factor in the fact that ChatGPT usage is unmetered", i.e. you get unlimited ChatGPT threads that don't eat into your codex limit

I am saying that because ChatGPT usage is unlimited, I don't have to eat into my Codex limits when I use ChatGPT. Codex certainly has limits. Last time I had a Claude sub (hedging here since much of the info in my comment was outdated), my usage limits on claude.ai threads was shared with Claude Code.

On usage in ChatGPT settings, I see: Plan limits Shared across Codex, Work, Workspace Agents, and ChatGPT for Excel. Chat conversations are not included.

Is this not the default anymore? I am on the (now closed) 20x plan.

I actually haven't played with the GUI. I probably should now that the Linux version is in beta. My situation is kind of the reverse: I like using oracle to basically zip up my repo, ask GPT Pro to propose some sort of design or refactor based on the code, then provide a step by step implementation plan for a cheaper model to implement directly in a harness on my machine. It often takes upwards of 90 minutes to come up with something but I've never been disappointed by the results. I suppose I could do this and then save a step by referencing the oracle-created thread with the @ you mentioned

And re: the toml workaround, AWESOME! I appreciate you pointing these two things out, this is my highest-ROI HN comment thus far.

I felt this way with Sol in the 5.6 series and was one of the seemingly few people on this earth who liked Terra for that reason. I would often have a very specific code-manipulation ask, e.g. "add a parameter to this method, ensure all callers pass it in, if there is not a logical way to derive the parameter to be passed in a particular instance, flag this in your final response", and Sol would go on some rabbit hole side quest to refactor my codebase to determine some way to derive it rather than flagging it as I had asked.

Terra had the "workhorse" quality where it could do these changes in bulk and follow directions without being too 'smart' (but sloppy) as you described. Luna was a bit too dumb and would make sloppy mistakes; I see that more as a "run these tests and format the results" sort of model. Maybe 6 Luna will be better.

I also just reread your comment and realized the naming convention is still extremely confusing with respect to ordering of [Family]x[Model]x[Number].

Every place I've worked at has positioned their SEV review process as 'blameless' with respect to the engineers who created the code, processes, etc that led to the incident. On paper, it's not about pointing fingers (though I've found this to be somewhat idealistic), but about finding faults in the processes that let bad code slip through the cracks.

It will be interesting to see how the notion of 'responsibility' carries over as agents handle higher and higher levels of abstraction. Agents built using the popular frameworks of today are somewhere in between code, formerly written by engineers, and an actor (like an engineer). When an agent wrote the framework to audit and monitor ops agents who are monitoring the performance and reliability of the code that coding agents wrote, who is responsible for ultimately ensuring it doesn't happen again? Should the findings just be added to whatever RAG and a few prompts/hooks/skills changed by another agent? When does a human follow up and to what degree?

This is the sort of thing that makes me believe that software engineers will never truly go away; at the very least, they serve the very useful function of being ultimately responsible for something going wrong.

> Who ultimately determines the meaning of a public space: its designers, authorities, or the people who use it?

Restrooms are unique in that they are available to the public but, due to their inherently private nature, are a place where it is difficult to enforce social norms. Because of this, within the confines of the restroom itself, the authorities are all but irrelevant.

I was scrolling through the addictive and easy to stumble into YouTube reels feature and came upon a livestream of a gentleman having some sort of 'public restroom party' in a stall. By this, I mean he had collected every roll of toilet paper available, shredded them into confetti, and was throwing the confetti up into the air while blasting music at full volume out of his bluetooth speaker. He had a few thousand viewers and people appeared to be donating money for supercomments. I didn't stay to watch the end of the livestream, but I don't imagine he cleaned up.

By the time the private-but-livestreamed confetti party is over, the damage is done. You can try to anticipate every single unwanted activity in a restroom and try to prevent it beforehand (e.g. tinted lights to prevent IV drug use), but someone, somewhere will find a way to creatively make the owners decide a few frustrated customers who are told "no public restroom" is a small price to pay for the alternative.

Agreed 100% for the consumer case: an empty chatbox is just about the least sticky surface I could ever imagine. I saw a mobile interstitial ad for Kimi recently whose hook was basically "Tired of paying for expensive ChatGPT? Download the Kimi app, it's the same thing but cheaper". I myself bounce between token subscriptions like no one's business and use Pi/OMP for maximum model flexibility when coding (and it's a few env variables or lines of (TO|YA)ML|JSON to switch providers in Codex, Grok Build, CC). I even self-host and try to use OpenWebUI + CLIProxyAPI when I can for all my chats.

Enterprise is a whole different ballgame IMO with countless technical, compliance, and employee adoption considerations that add friction to switching. It's also where both Anthropic and (as of last week) OpenAI get the bulk of their revenue, and, incidentally, the venue where US Government regulations on Chinese models would have the most impact.