> Read my other comment in the thread. Why would I post a non-sincere comment on this anyway? HN is social media, saner than most, but I still don't assume sincerity. > Yet, saying this simple stance just as I did now,…
> not resentful or passive nihilism To be more precise, it was passive nihilism I was criticizing. That's the sentiment I sensed in the original comment.
I don't know how sincere this comment is, but if there are others thinking this way, it's a mistake. Nihilism is a dead end. Social media is a veil of manipulation, and bots. Do not misconstrue it as any kind of real or…
If AI is so capable and intelligent, I can just ask it to prepare me resources to learn about "real work in code repositories" and "AI fluency and judgment" and "agentic development environment", right? Why exactly is…
Note that paper is saying that the lean proof and the natural language proof do not necessarily coincide. It is not saying that the lean proof is wrong, just that the lean proof does not necessarily mean the natural…
Oh yea, completely misread that. But still, it's been my experience that TPS is much _lower_ on Sol 6.1 than Opus 5.5. To the point that 6.1 takes forever to finish a task. They did speed it up in the last few days, but…
> The notable difference to me is tokens/sec are still much higher on 6.1 Sol This is also the reason why I'm swapping over to Anthropic for a month. 6.1 Sol seems good, but is unbearably slow even with 6.1 being more…
No public repo but it's not too difficult to point a LLM at the general idea. Since Codex is open source, you can even take a look at how they do it. Here is what the model is instructed to do in codex (look at…
One approximation of this is the experimental context management Codex has been moving towards (not released yet). Rather than relying on summary compaction, the model maintains notes as it works and as it approaches…
I hope more open weight models are released, with more Cyber capabilities and with no limitations.
I don't understand why they didn't call 6-Sol just 6-Terra. It was 5.6-Terra level pricing with a perf jump.
Yes but it was underwhelming, so the seem to have rushed 6.1 Sol out.
What's with slop-factories forgetting what a README is supposed to be? A quick intro to the project, not a gigantic abomination with irrelevant details.
I don't know how good of a marketing ploy it is, tbh. Considering it paints them as incompetent, and that they cannot be trusted with developing this technology safely.
Also note that Opus 5 (High) has an index value of 62, vs Fable 5 (Max) has 61. So some strangeness going on with that index.
I have some doubt about AA-index. For example Opus 5 (High) is at the index value as Fable 5 (Max), I wonder if that's really true.
One issue I see with including something like Pi is that it's intentionally bare bones. I don't think anyone uses Pi without some basic custom extensions (subagents, check lists, etc), so this benchmark may not be…
I would expect the benchmark scores to be nonlinear near the top, as the easier tasks get solved and the harder ones are left over. So going from 10 to 15 would be easier than going from 60 to 65. I only take the…
From Artificial Analysis cost per task, it looks like Fable 5.1 is more expensive per task than Fable 5? Cache hit price went down, but the other components still add up to more. Edit: 5.1-xhigh seems to be cheaper than…
All of this stuff seems like a band-aid solution. These things need to be trained ground-up to have some sort of memory, perhaps out-of-context memory. Also seems like a requirement for any sort of continual learning…
What's going on with sol here? The note says it spends a lot of time waiting, did it just not effectively use time (i.e. something like parallel runs) so it's graph ends up being stretched in the time axis?
Also with Qwen 3.8 being more token hungry than Luna, using around 2.3x tokens. Which hurts for local deployment.
One line of evolution seems to be toward some form of latent-space reasoning, as in [1]. Natural language seems like a relatively low-bandwidth channel for intermediate reasoning. [1]…
I've never found these discussions to be all that useful, because it's hard to define what conditions are sufficient to say something is "thinking" or "reasoning". It just ends up being circular and metaphysical…
You are making two different claims, and then treating them as one. 1. Mimicking a process may not prove that the system is truly preforming the same process. In this case, a "reasoning" process. 2. A system that…
> Read my other comment in the thread. Why would I post a non-sincere comment on this anyway? HN is social media, saner than most, but I still don't assume sincerity. > Yet, saying this simple stance just as I did now,…
> not resentful or passive nihilism To be more precise, it was passive nihilism I was criticizing. That's the sentiment I sensed in the original comment.
I don't know how sincere this comment is, but if there are others thinking this way, it's a mistake. Nihilism is a dead end. Social media is a veil of manipulation, and bots. Do not misconstrue it as any kind of real or…
If AI is so capable and intelligent, I can just ask it to prepare me resources to learn about "real work in code repositories" and "AI fluency and judgment" and "agentic development environment", right? Why exactly is…
Note that paper is saying that the lean proof and the natural language proof do not necessarily coincide. It is not saying that the lean proof is wrong, just that the lean proof does not necessarily mean the natural…
Oh yea, completely misread that. But still, it's been my experience that TPS is much _lower_ on Sol 6.1 than Opus 5.5. To the point that 6.1 takes forever to finish a task. They did speed it up in the last few days, but…
> The notable difference to me is tokens/sec are still much higher on 6.1 Sol This is also the reason why I'm swapping over to Anthropic for a month. 6.1 Sol seems good, but is unbearably slow even with 6.1 being more…
No public repo but it's not too difficult to point a LLM at the general idea. Since Codex is open source, you can even take a look at how they do it. Here is what the model is instructed to do in codex (look at…
One approximation of this is the experimental context management Codex has been moving towards (not released yet). Rather than relying on summary compaction, the model maintains notes as it works and as it approaches…
I hope more open weight models are released, with more Cyber capabilities and with no limitations.
I don't understand why they didn't call 6-Sol just 6-Terra. It was 5.6-Terra level pricing with a perf jump.
Yes but it was underwhelming, so the seem to have rushed 6.1 Sol out.
What's with slop-factories forgetting what a README is supposed to be? A quick intro to the project, not a gigantic abomination with irrelevant details.
I don't know how good of a marketing ploy it is, tbh. Considering it paints them as incompetent, and that they cannot be trusted with developing this technology safely.
Also note that Opus 5 (High) has an index value of 62, vs Fable 5 (Max) has 61. So some strangeness going on with that index.
I have some doubt about AA-index. For example Opus 5 (High) is at the index value as Fable 5 (Max), I wonder if that's really true.
One issue I see with including something like Pi is that it's intentionally bare bones. I don't think anyone uses Pi without some basic custom extensions (subagents, check lists, etc), so this benchmark may not be…
I would expect the benchmark scores to be nonlinear near the top, as the easier tasks get solved and the harder ones are left over. So going from 10 to 15 would be easier than going from 60 to 65. I only take the…
From Artificial Analysis cost per task, it looks like Fable 5.1 is more expensive per task than Fable 5? Cache hit price went down, but the other components still add up to more. Edit: 5.1-xhigh seems to be cheaper than…
All of this stuff seems like a band-aid solution. These things need to be trained ground-up to have some sort of memory, perhaps out-of-context memory. Also seems like a requirement for any sort of continual learning…
What's going on with sol here? The note says it spends a lot of time waiting, did it just not effectively use time (i.e. something like parallel runs) so it's graph ends up being stretched in the time axis?
Also with Qwen 3.8 being more token hungry than Luna, using around 2.3x tokens. Which hurts for local deployment.
One line of evolution seems to be toward some form of latent-space reasoning, as in [1]. Natural language seems like a relatively low-bandwidth channel for intermediate reasoning. [1]…
I've never found these discussions to be all that useful, because it's hard to define what conditions are sufficient to say something is "thinking" or "reasoning". It just ends up being circular and metaphysical…
You are making two different claims, and then treating them as one. 1. Mimicking a process may not prove that the system is truly preforming the same process. In this case, a "reasoning" process. 2. A system that…