Anecdotal, but I tried running a few identical biology questions through both Fable and Opus and the classifier was only rejected my queries with Fable.
This is good news. I'm doing a lot of work that Fable thinks is AI related right now (it is nothing remotely competitive to Anthropic - it's just relatively basic stuff I'm doing with learning models and so forth), yet it blocks me almost every time. I have switch to GPT-5.6-Sol for this work since it's stronger than Opus 4.8.
Any previewers have hot takes? I've really preferred gpt-5.5 over Opus 4.8 for data analysis and scientific software work. It seems much more reliable. Fable is unusable for the type of work that I do (due to guardrails). Really looking forward to trying these new OpenAI models out.
Interesting to hear people like gpt-5.5. For me it feels smart only at one shot prompts, but if you try to build up session context before doing something it feels magnitudes inferior to Claude.
I'm almost sure its because the thinking of previous turns is stripped with the responses API, so if I tell it to analyse something deeply, what remains of the understanding in future turns is only the short response text of that analysis
For gpt-5.5 I build up that session context into a markdown file, and then I start a new session and give it the markdown file with the instructions for what to do.
I'm guessing this works better because it can always go back and re-analyze the saved context.
Do you have a source for this? I'm pretty sure responses api is only there to obfuscate reasoning, but that they're still keeping reasoning traces in the backend.
> Input and output tokens from each step are carried over, while reasoning tokens are discarded.
Keeping reasoning tokens around is better for caching and for remembering past insights, so you might reasonably wonder why we designed it this way. The main benefit of dropping reasoning tokens is that you can fit a lot more work inside the model's context window before you're forced into a slow and lossy compaction step. This was a larger consideration with our earlier reasoning models that had shorter context windows (~200k), longer thinking times (up to ~100k per message), and poor compaction. However, now that we've shipped longer context windows, we've trained our models think much more efficiently, and we've made compaction way better than it used to be, the balance of factors is changing. Tune in Thursday!
> fit a lot more work inside the model's context window before you're forced into a slow and lossy compaction step
This is something I never understood. Why the reasoning is not included until the context is full, then the reasoning stripped optionally to allow the conversation to continue. and only then when its truly full offer a compaction. Was it to optimize caching? Well I guess it doesn't matter now that you hinted that this choice was made because of prior limitations and may change very soon
> Why the reasoning is not included until the context is full, then the reasoning stripped optionally to allow the conversation to continue. and only then when its truly full offer a compaction.
Models are typically trained (at longer conversations/more turns) either with or without the reasoning still in the conversation. If you train a model with those, then using it without them, the model will perform a lot worse, same vice-versa if you train without but then end up using the model with them.
That's why you'll see some models have it and others don't, and trying to use them another way, will make them worse, they weren't trained like that.
So why aren't the models trained with both? I'm guessing that sort of permutation in the training would lead to double the amount of training time being needed, as you know effectively will have two variants of every session you train on, with and without the reasoning.
Well, obviously its true as you can see in the silbing comment. But still interesting how experiences differ. I wonder did you ever use codex in more demanding workflows, because that at least something like that is going on is obvious if you use it for a few hours
You answered at more or less the same time as an OpenAI engineer confirming this is the case, explaining why they did it, and pointing to their docs that also very explicitly explain this "made-up nonsense". You should really consider why you felt so certain about something you were plain wrong about.
> thinking of previous turns is stripped with the responses API
Why do they store an encrypted reasoning payload in the session file and pass it to the API? Just a ruse? Reasoning isn’t even that many tokens, you think they’d degrade their model quality like that?
Reasoning messages would be lost immediately after a single tool call, unless you mean they sometimes go back and strip the reasoning channel retroactively, but that would increase costs via cache invalidation. I just don’t see any way it would make sense for them to do.
And wouldn’t this be noticeable by reasoning tokens not being accounted for in the context window usage?
For compiler work I found that Sol is noticably better than 5.5 (and I generally use OAI models because I like the Codex app), but Fable was still obviously better.
Better in what way? Does it follow the goals better, does the code produce have higher quality in a testable/maintainable sense or is it just closer to how you would usually program something?
I'm sorry to hear you are unable to use Fable; my partner is in the same boat and it frustrates her immensely to see what I've been able to do with it. As someone who is working with developing new linear algebra routines, Fable is so far ahead of GPT-5.5 and Opus that it's obscene. Massively better insights and far better at handling delicate corner cases without needing to mention them. I would be stunned if GPT-5.6 is at that level, but one can hope.
This is a cool idea—I know from snooping on sumbit scripts and node utilization on the HPC that I use at my institution that most submissions leave some compute on the table (and many of them are egregiously bad). I'd probably vote in favor of sending every submitted sbatch script through an LLM (at least for everyone else, I'd would prefer tuning my own usage myself :) ).
Presumably the underlying model here is also an LLM? To what degree is it "fine-tuned", or is it just given a set of tools to build a good picture of cluster usage?
Nope :) the core model isn’t an LLM. It’s a custom architecture built from the ground up. We natively accept multimodal inputs such as source code, submission scripts and hardware topologies. The LLMs in the post are the baselines we beat.
This is also why fine-tuning matters for us. We train a cluster-specific model that gets better as more jobs run on your cluster, because the same code behaves differently on different topology. An LLM reasons about code/script in a vacuum with no native sense of how your nodes actually perform
I wonder if the tendency to write short punchy sentences stems from deliberate RL efforts to avoid repetitive, consistent writing? I seem to remember that a critique of early LLMs was that they would produce sentences whose construction was too homogeneous. Would be interesting to know the answer to this.
You could say something similar about biology—just physics behind the curtains, and we understand a lot of the basics. The difficulty comes from complexity, not mysticism.
To be clear I don't think that LLMs are sentient, but the appeal in studying them is similar to biology in that you get to dissect a highly complex system with comparatively crude tools.
It feels like a lot of the folks who occupy the same biotechnologist genre as Venter (George Church, Eric Lander, etc.) can come off this way. I agree fully about the grifty nature of aging and longevity research (mostly because of the target audience), but I also think that you need an element of this willingness to entertain ideas that are borderline crazy to get to their status in the first place. Proposing to sequence (or, perhaps more timely—edit) the human genome would have seemed like a wild idea in the 80s, and yet they were thinking about it.
The end of this short interview with Stuart Schreiber has a similar vibe:
Note how interested he is in consciousness and AGI. This is something that he's been talking about for a long time, just formulated differently. You need to be able to temper true scientific rigor with a little bit of wackiness to even think about tackling these big questions.
This looks interesting and I will give it a try. I agree that the space-switching animation is painful.
I don't however think that this will solve spaces on MacOS, for the simple reason that opening new instances of apps is inconsistent and often doesn't behave how you'd expect it to once one more than one space is involved (in my experience, anecdotal).
I've come to peace with the fact that I will never be able to simultaneously experience the productivity of i3 and the necessary evil of MS Office/Illustrator on the same OS. The most important factor in my work is who I work with (rather than what I work with) so I'll remain on the latter train for now.
> for the simple reason that opening new instances of apps is inconsistent and often doesn't behave how you'd expect it to once one more than one space is involved
System Settings > Desktop & Dock "Automatically rearrange Spaces based on most recent use". This is the critical part.
And then right click App on the Dock, Assign to this Dock.
With these two things, Spaces becomes predictable and repeatable.
> There are only two problems: for one, yabai does this by binary patching a part of the operating system. This is only possible by disabling System Integrity Protection at your own discretion. For the second, installing yabai forces you to learn and use it as your tiling window manager1. I personally use PaperWM.spoon as my window manager. Both of which are incompatible when installed together.
I was referring to their last line ("I will never be able to simultaneously experience the productivity of i3 and the necessary evil of MS Office/Illustrator on the same OS") not the linked article because the parent doesn't "think that this will solve spaces on MacOS" therefore I gave a suggestion that would.
Secondly I don't find anything that bad about why the article's author doesn't want to use yabai, I generally disable SIP anyway (because I want to install anything I want without restriction, even edit system files because that's necessary in some cases, as yabai does); and they just don't want to learn a new WM which is fine for them but isn't a valid reason for everyone to not use yabai.
For example, there are rings of accounts posting generated comments, presumably in order to build karma for spammy or (let's be kind) promotional reasons. There are also plenty of spam rings that create tons of accounts and whatnot.
These are different from the submitter-passed-a-link-to-friends kind of upvoting and booster comments, which feel quaint by comparison. In this case people usually don't know they are breaking HN's rules, which is why they don't try to hide it.
"No stupid rules of engagement, no nation-building quagmire, no democracy-building exercise, no politically-correct wars. We fight to win,” Hegseth said."
It's a self-soothing performance of self-importance, like everything else this administration does.
This is not an administration run by adults who model consequences.
Everything happens to reassure the Commander in Chief - and the people behind him, like Miller and Vought - that they're exceptionally special and gifted people who can have anything they want and do anything they want, to anyone, without limits.
There's pretty clearly negative value in having civilian leader whose most notable accomplishments are being a TV opinion host, and quitting the Army because they decided he was too dangerous to be allowed to serve as a guard for a presidential inauguration.
To understand this rhetoric, you have to understand how important American Football is to the majority of the voting American public. We love a team that hits hard and wins the trophy! The good guys winning! What’s better? Have you seen any of the Marvel movies? The objective good guys always win! Win win win
I live in a deeply rural area. Nobody is like this in regards to war. I wish I could put on blast the deep worry I see everyday. Perhaps there is a cultural difference between the rural and red cities? It's hard not to take note of drafting the entirety of your young family to go shoot guns and die even if it was 100 years ago.
