While AI has made my life as a developer worse in many, many ways, I am conversely really glad the conversation has shifted past these types of tricks, framework wars, etc.
No kidding. Seattle has almost nothing left, except an AM station and a few shows on mixed format stations. Chicago's top shelf if you're hunting for online. They have lots of choices, just depending on your particular need / mood.
Power 99 was 98.9 WUSL (I looked it up to be sure). All I could recall for sure was "Power 99...FM". Heh.
Reading Frontier’s website it’s very unclear how much they’re going to remove and how they’re going to do it - though there’s a lot of mentions of biomass
Trouble with techies is they tend plumb for techie solutions like carbon capture aka ClimeWorks rather than low tech options like trees or seagrass
Trees and seagrass don't really address the sequestration side though, do they?
The carbon they latch onto and temporarily hold onto is still within the land / sea surface +/- a few metres layer.
The current largest scale carbon capture projects are catching a small amount of vented CO2 from LNG projects and pushing that back into the subsurface fields - they only capture 10 ton by releasing over a 100.
We're in need of readily powered true air capture of CO2 then sequestered deep underground.
Things like www.sciencedirect.com/science/article/pii/S036031992602269X have promise.
Trees and seagrass can address the sequestration side.
You can find examples here on Frontier's site of companies that are taking biomass (plant stuff like tree waste) and sequestering it in mines or other storage deep underground.
When thinking about sucking carbon from the sky, I find it useful to separate how I think about grabbing on to carbon dioxide from how to store carbon dioxide, rather than thinking of it as one step. I find it's easy to get lost and either over or undervalue things otherwise.
Plants and trees are excellent at grabbing on, for example, and with a good process they can lead to very cheap methods to store/remove carbon dioxide for a thousand years.
I appreciate the response and note that it's precisely because I already separate both the acquisition of CO2 from the sky and direct acquisition from industrial processes well apart from the storage side that I correctly stated trees and seagrass aren't storage methods.
How it's stored (and the energy used to store) matters. As you know - there's not much to argue about here, just a nod that it's best to be careful with words.
As a further question, what's the most effective Direct Air Capture method actually working on your books so far, in terms of greatest tonnages, and where is that captured CO2 being stored.
Thanks I’ll have a proper read of the paper when I’m on a larger device
Generally I’m skeptical of Carbon Capture and Storage schemes (and Hydrogen) as it’s a way for oils and gas companies to delay the transition to cleaner energy
IMV hydrogen does have something of place in industrial processes e.g. reduction of iron ore, and maybe fuel cells but not for general combustion
Reading this really makes me wish that I had a slightly better workflow. I'm really soley dependent of Fable to the point that I don't use other models, and I've already sort of hit a point where I'm running into usage limits every week. I am really living on borrowed time — when Anthropic finally collapses their 50% usage increase at the end of August, I'll definitely be forced to switch my workflow. When that happens, I have a hard time imagining that I'll be sticking with a single model on a single provider.
> Reading this really makes me wish that I had a slightly better workflow. I'm really soley dependent of Fable
Good thing then that you're fully in control of your own actions.
A gift granted to us by being a fully grown adult that is also likely registered to vote.
Meta: There is of course a way to put this less snarky, but that doesn't slap people in the face as hard as they need to be slapped in the face to maybe one day start remembering that they have agency.
> when Anthropic finally collapses their 50% usage increase at the end of August, I'll definitely be forced to switch my workflow
I cancelled my Anthropic subscription until they fix how their models write and it's no longer unbearably annoying and obnoxious. The concise output format is a step in the right direction but I need a few months away from them.
Kimi and GLM models on Max reasoning feel pretty close to Fable. That said, even at their most expensive plans, a single one of them might not always be enough, while getting both of them for a year gives you a nice discount and isn't insanely more expensive than Anthropic. The problem there is that they could still easily rugpull you with token limit changes later, I don't trust any of the big labs not to mess around with those for any length of time.
Also most harnesses let you choose models per sub-agent. Like I can use Fable for running the main session and just tell it to use Opus agents for implementation in Claude Code, same with the Kimi and GLM models inside of OpenCode and other harnesses. The only problem is that the UI for controlling sub-agents usually really sucks.
Yes both Opus and Fable’s comment style is truly unbearable. I like the code result but it’s so annoying seeing it reflect our conversation as code comments.
On the flip side, a lot of the reasoning and decision making might have happened in the conversation which is more ephemeral than a comment. A future LLM-age source code repository would store the conversation along with the commit, for future reference by humans or LLMs.
I only like talking to Opus 4.6 in its default form. I have some pretty aggressive prompting strategies ensuring my language guidance rules are front and center and it really helps with Opus 4.8+, something went wrong with those models.
Also, OMP has a solid subagent model and I like it with some tweaking.
I've been using GPT-5.6 Luna for everything at this point. It is more than enough to do all the work I need to do. You have to lead it by the nose, but if you know where you're going it works really, really well.
It seems there are two distinct groups, one which is doing relatively well with Luna, Deepseek Flash and similar models while other seem to be satisfied only with the state of the art.
Depends on how in-the-loop you want to be. I personally delegate all the writing of the code to agents, but I maintain a clear mental model of the architecture, which I come up with by iterating and prototyping with agents. I can use Luna for all of this, although I switch depending on the task. It's nice to be able to throw a 1,000 word rough spec at Fable and get a personal tool that works perfectly though. I expect that as the models get better, I'll continue to be in the loop, but operate at increasingly higher levels of abstraction.
Having worked with both, it seems like a control thing to me. Either you're cool with Fable spitting out tons of code you'll never read, or you're cool with Luna doing targeted work while you manage the main work thread.
(I'm in the second boat so long as I'm responsible for the code I PR)
I'm ok with not-Fable until I need anything design-related: a nice HTML page, LaTeX typesetting, UI design. Sol is especially incapable of doing anything sensible.
Is there any alternative model with design sensibilities?
Did you add some skill for this? I've been using a frontend design skill with Sol and it's reasonable (for my purposes). I don't remember where I got that skill.md though, it probably was from OAI's own blog about this a few months ago.
fable is good at it but I find it uses the same slop in different variants every time. Even the words it uses for the different alternatives it proposes are the same (cartography, atlas, bench, signal, etc). At least you develop a good nose for slop ;) it becomes a struggle to steer it off the same path every time.
I'm happily in both depending on what it is. Even Sol / Fable cannot do some truly novel stuff and if you rely on it too heavily you get detached from the underlying systems to the point that it's both uncomfortable and detrimental.
I’ve just been using it, with a chat interface. Basically, as a “consultant.”
For me, and my projects, it’s been great. It’s made an enormous difference.
I guess my workflow may seem “quaint,” to many folks, here, but the end results speak for themselves.
I suspect that one vocation that could get heavily impacted by AI, is the consulting business. That’s where many experienced people go, as they reach their career peak.
In my last project (just about to ship), ChatGPT replaced a whole bunch of services that would usually be supplied by external advisors.
But these are also services that I would normally not be able to afford, otherwise, and would just have to “make do” with. This release will have a level of polish that I have would never been able to achieve, unassisted by AI (I had originally used “on my own,” there, but the reality is, it actually was “on my own”).
The thing about consulting is that someone needs to verify the output, know what questions to ask in the first place, and provide a throat for the client to choke in the event of an issue. Also, professional insurance. I could be wrong but in the worlds I live in professionally, accountability is still a thing.
Yup. There's some places that we'll need that accountability. I suspect that this may be filled by folks that act as "LLM brokers," using AI in the background, while dealing with the legalities, in the foreground.
But in my case, it wasn't nearly so exotic. The LLM helped me to do a much better job, preparing the App Store presentation, Web support, privacy policies, budget prognostication, and app glossary.
I have just had an extremely complex app, pass App Review, in record time (from going into review, to approval). No niggles or bounces at all.
I'd be curious to pick your brain about the process you went through for this. My mental gap here is not even knowing what to ask for a process like this.
Happy to do so. Probably not something a lot of folks here would find interesting, but I'm easy to contact, from my Web sites. People here, often do that.
Basically, my needs are different from others. I'm not working on the next NORAD upgrade, much of my work is open, and the more ChatGPT knows about me, and the app I'm designing, the better. One reason I chose it, was because of this "memory."
TL;DR: I feed it just about every scrap of information about my project as I can. Source files, documentation, screenshots, videos, information about the organization, information about the target demographic, etc.
With all that information, it gives me very useful advice.
It created a great tutorial. I usually write way too complicated ones. It did much better.
In the case of the App Store stuff, it helped me to choose the right privacy report, generated the privacy manifest, and helped me to compose all the copy on the storefront.
I'll probably be releasing the new app, soon. It's already passed review, but I want to make sure that everything is kosher, before releasing. It came together so quickly, that I have the luxury of time. I just need to release before (or as) iOS27 comes out.
Oh, I don't really do much more than have feedback loops, where I review the output, then ask for things like less verbosity, or a lower-level vocabulary, etc. I like to apply this at each application, rather than make a blanket rule, as each page may have a different audience.
For example, I have made a tutorial, which is meant to be a "quick reference," from within the app (Use Safari to view the page), but I am also developing a "walkthrough," to show possible funders (we're an NPO). The walkthrough is a higher-level vocabulary than the tutorial. The LLM deals with stuff like making sure to keep the glossary consistent, etc., but I like to have the final say on the output.
I'm pretty sure that I can force the LLM to use certain levels of vocabulary, through the .md file that describes the default setup, but choose not to do it.
I am still in that "trust, but verify" stage of my relationship with LLMs.
Same, all I need is speed to execute editing faster than I could in vim. Luna is cheap, intelligent enough, and fast enough I don’t lose the sense of flow.
Sol is basically at the same level, but with better usage. You're not dependent on Fable. You could switch the next minute and hardly experience quality differences.
My experience of Sol is that it's very instrumentally competent but is a complete terrorist that will cheerfully do unhinged things that "technically" solve a problem. For example, I asked it to verify something in our integration tests and it responded by grabbing kafka details out of config and trying to use them. When I pointed out that this was not it, it did the same thing with a database client instead. Conversely, I'm pretty sure Fable or even Opus would have done something consistent with what the rest of the codebase does (consume an API or point out that there's no API to access in this case).
I don't have Fable at work but I'd probably use it for actual code if I did because not having to spend time handholding the model on this stuff and getting useful code first try is very useful
What I do notice is that when it doesn't have the info it needs, or when I don't tell it that I'll handle part of the process, it will indeed do everything to get the job done. Also saw this but find this a great quality, because I never ask it to do anything that would involve unhinged things. Sol and other models as well have just gotten so damn good. They can get just about anything done and usally do it well too. Maybe I was inexperienced in prompting, but I remember doing much, much more handholding with late 2025 LLMs.
Once it has exactly your coding conventions and access to other code to copy bespoke patterns, a strong idea for what to do, then you can let it do the work.
Sonnet 5 is the worst model of 2026. Literally just turn effort slider down on Opus, it's smarter, faster and cheaper than whatever Sonnet is.
Beyond that, I find this whole plan and build thing to be a pointless waste of tokens. If your planner made a detailed enough plan, then the cost of executing that plan is a just one turn more of cached tokens, and minimal time.
Meanwhile: switching agents, reloading context and building from the plan will easily balloon your token use and time. And any emergent problem that the dumb executor finds will instantly wreck the implementation because they're not competent at solving it. And if your plan is so perfect that there's no edge case then you're wasting tokens because your planner was one turn away from finishing the project via cached tokens.
Completely disagree (except the Sonnet bit, yes, it's degrading).
"then the cost of executing that plan is a just one turn more of cached tokens, and minimal time."
This is just not true at all. There's a huge gap between 'figured out the hard stuff' and 'rock solid'.
Dependencies, integration, corner cases, docs, testing, unforeseen issues, a lot of back and forth auditing making sure things are really tight.
Audits get diminishing marginal returns, but you have to do them until they don't find anything, and that's usually a few cycles.
So aside from the fact there is 'a lot of labour' - part of the plan (maybe the most important part) is documenting most of the trip-up scenarios. If you ran an experiment or two in the background your agent will 'discover' a few key odd things, you back those into the plan.
I'm 100% certain that this pattern works because I (and others) use it very successfully.
Hint: save your main context by using sub-agents to do grunt work - even in impl phase - farm out anything directly implementable without a ton of background.
Also - make a skill so your Claude can call Codex and visa versa and maintain long-running sub agents of 'the other kind'.
An Opus with 1M context window executing on a 'plan' that a Codex 'sub-agent' is executing on - ad a different Opus sug-agent is auditing hard ... that 1M token window is dramatically extended to 'many millions of tokens'.
I'm sorry, but just because you achieve results you consider acceptable with this method doesn't mean everyone does.
I don't work where we can ship slop. I don't work where PRs can be merged based on what the agents say. I work where a human has to read and approve and own every single line of code. I work where the stakes are actually high, so the cost of not using the best tools in terms of human time are big. A single turn around in a PR costs more in human time than the difference between deepseek and fable in API costs.
So, when you admit "There's a huge gap between 'figured out the hard stuff' and 'rock solid'." but then claim that the cheapest/dumbest agent in your arsenal is your go-to for "rock solid", I have to question the quality of your results.
Personally, "using plan mode" is a very 2025 way of using these tools, and I wouldn't be surprised to see "plan mode" be removed from codex/claude code/et al.
Realistically, I'm using the best models to think about a domain and problem (Fable High+), and I'm using a cheap daily driver with an advisor pattern (Opus High + Fable) to iterate through POCs, and I'm using human review to guide design. None of that is "plan mode", it's actual engineering. Then we decompose the solution, we stack it, and we use only really strong agents to build, review and refine.
This obsession with cheap agents leads to low quality outcomes. "Rock solid" deserves the best tools, and the "plan" will never be good enough. I'm going to be sending fable xhigh and sol 56 xhigh et al at it in adversarial review, why the heck am I cheaping out on the actual implementation?
And finally: my time costs way more than any of this. Cheaper models are slower overall and when combined with re-work time, are dramatically slower. I'm costing my company hundreds in my time to save a few bucks on the API bills. Nonsense!
Yours was the casual dismissal; and based on a misunderstanding of what can be achieved.
Based your arbitrary dismissal and unwillingness to even try to consider new patterns with which you may be unfamiliar - it may be difficult to communicate with you.
I have the advantage of 'certainty' because I have the evidence over many projects / team members.
We ship near perfect code.
In addition to the hints above, we do this at least in part by explicitly anchoring and testing requirements into several aspects of the code, and ensuring that known 'weak spots' are managed.
The 'planning process' ensures the requirements are mechanically anchored and integrated into tests, that 'proportional' documentation is applied, and that module, library and project level documentation is perfect (and mechanically validated where possible), which FYI is what solves most of 'context problems'. (That's another hint, if you have extremely good docs, you don't need to load vast amounts of code).
Yes - I hear you that 'time matters' and that 'the stakes are high' - consider that you may be talking to people where the stakes are just as high, or higher - but more specifically, this is not about 'saving tokens' or cost so much as it is using the right level of model for the task.
Use the best models for background research and planning, use mediocre models for execution, and mid-high for auditing - in other words 'use the right model for the right work' - and in a certain methodology, dumber models are appropriate.
FYI this saves you the ugly 'Fable' problem which many are encountering as it burns though Max plans. Don't 'automate' with Fable, it's the wrong model for that.
I could go on, but consider that there are actually ways of organizing projects and orchestration that work well.
If you find yourself wishing for more Fable at the subscription rates, just buy another 20x account? I'm currently on 3, spaced out on Sunday, Wednesday and Friday. Just as one is running out the next resets. Problem solved!
I feel the value I get far exceeds $600/m. It's a straight expected value calculation for me and I'm happy to pay. I wish they'd make it easier though - just sell me a 100x account for $1k/m and save the messing around.
what kind of workflow are you using the requires that many tokens? I rarely hit my limit with the $100 a month plan and I use fable pretty frequently although it usually acts as an orchestrator while the actual work is done by lesser models usually.
Nothing weird or exotic - just frequent daily work in two reasonably large applications, with a lot of testing and follow-through. I've found that as codebase size goes up, token usage does too - perhaps quadratically, and a complex back end application just costs a lot to work in, probably because it needs to map out so many pathways and interdependencies.
I tend to work in 5-10 or so parallel streams at a time so that also multiplies token use as a function of time. Much less and I'm waiting for it too much, much more and I can't juggle effectively. My new big project is of course to try to take myself out of the equation further and increase the parallel streams dramatically; pretty hard to get that right so still manual for now.
Fable is pretty good at routing to Opus and Sonnet though, especially if you ask. also, sometimes just because it decides that's what it feels like doing at that point.
The GPTs are just as good and I can trust many tasks to open models. Autonomous coding is best with frontier class models but steered coding is fine with even DeepSeek V4 Flash.
I am actually going to guess that this is in fact unfortunately not an LLM. I have been made a few audio webpages and don’t think a lot of these mistakes would have been made, even though the model can’t hear :^)
<!-- EXACT setup from working simple-test.html -->
<!-- Chiptune3 now loaded via Vite build system -->
are pretty stark llmisms. also the random emojis in front of the duplicate and triplicate "Browse Music" links, the corny tagline in the footer, yeah nah. if this was made by human hands, it could only have been as elaborate satire. bad/inexperienced human code does not look like this.
> <!-- EXACT setup from working simple-test.html -->
All LLM-kind would be vastly improved if the words "exact" and "brilliant" were nerfed to hell in their pre-training weights or even just removed from their training distributions entirely. Virtually nothing outside of mathematics is "exact", and virtually nothing outside of colors should be described as "brilliant".
Also basic functionality not working paired with awkward and vaguely nonsensical phrasing - search, show all, "Showing tracks from all groups.", queue all -> "No songs found in this group." And that paired with some otherwise relatively sophisticated techniques involved in the basic functionality.
LLMs are on occasion like a kid that can do a standing double backward somersault, but can't walk. It's the same tell you'll have in discussions online. Somebody will spew out extremely esoteric (and accurate) knowledge/concepts, but then demonstrate a complete misunderstanding (or lack of knowledge) of basic concepts in the exact same domain.
Similarly blessed that I am too stupid to comprehend this post.
This person compares themselves to Prometheus and is begging for cash? What? Why is this not flagged?
reply