mwigdahl

Sure, but the original comment said "living out" those fantasies.

I don't know -- it's not even showing Fable in /usage any more, in sessions that were using it just fine moments before. Seems more like a backend change to me.

You missed a great opportunity to title this "The 10 most popular numbers in Hacker News titles"!

For sure! It's possible there are relatively invariant properties that make one language or another "better" for LLM coding in general though (even if that's just the self-fulfilling prophecy of size of the training corpus).

“An honest caveat…”

There were a lot of European wars between the Napoleonic Wars and the First World War. I agree with your point overall but there was a lot of fighting each other during that timeframe.

Yes. It is great for analysis, debugging, and understanding larger segments of code. I'll use it sparingly since it won't be on subscription, but there are cases where it will make sense to use it.

I'm reading your story now -- it's great space adventure! Congratulations!

Apparently Fable got all the power when writing this...

Fable returning wrong answers if it suspects the topic is sensative

Citation, please? On the original release they downgraded models silently to Opus 4.8 when they suspected it was being used for LLM development, but they stopped doing that. Now when you hit one of the guardrail subjects it downgrades to Opus 4.8 visibly in all cases.

I've never seen anything suggesting they're deliberately returning wrong answers. Maybe you're thinking of Gemini's anti-distillation tech?

Unfortunately as cost reduction trends to 100%, it comes along with an intrinsic high-pass sarcasm filter.

Same (including the overthinking issue).

Hence the fading away of the "nerd with pocket protector" stereotype...

During the initial release, they indicated you'd be able to use Fable 5 as part of your subscription for a limited period of time, and then it would require usage credits. They also did say at that time that they hoped to make it a part of the subscription plans again at some point after that.

For this return, they've extended the usage period to July 7, but limited you to 50% of your usage quota, and have not restated the desire to make it permanently part of the subscription plans at some point.

I still have hope, but it's not moving in the right direction to be sure.

Sure, and if they hadn't trimmed logs someone would also be complaining that "stupid Anthropic lets logs fill your hard drive"!

Oh wait, they just complained about Codex doing this a day or so ago.

It's a good question, but for multiturn conversations even cached context adds up quickly. My experience has been that spawning off subagents for defined tasks in a large overall plan generally makes me come out ahead.

I'm sure folks' mileage will vary though.

I don't think all the negativity is from crazies, but big chunks of it are certainly motivated. I certainly left out numerous other categories.

For agentic computer use Sonnet 5 low performs better than Sonnet 4.6 medium at just under half the cost, and better than Opus 4.8 low at 25% off. Their success rates are not that far off.

Agentic search is a different story, but even there it still dominates 4.6 (as in, for everything Sonnet 4.6 can do, Sonnet 5 can do it as well or better at the same or lower cost).

Yes, Opus 4.8 dominates Sonnet 5 over its entire range in both categories, but Opus's lower range is limited and there is a valid regime on the lower end where Sonnet 5 use makes economic sense. This is not the case for Sonnet 4.6 where Opus 4.8 dominates it completely on both charts.

Edit -- reading your response closer I think we're saying the same things, maybe just disagreeing on whether that lower end is valuable or not.

Seems like a combination of multiple factors:

"They took my shit away!" -- 3-day Fable 5 addicts (me)

"How dare they tell Trump no?" -- US nationalist / "my country right or wrong" types

"Great to see a closed source company fail!" -- open source boosters

"Great to see an American company fail!" -- anti-US, and/or pro-China folks

"Great to see a successful company fail!" -- anti-capitalists and/or sour-grapes crab bucket types

"Serves you right for ripping off creators!" -- copyright warriors

"They keep silently nerfing the models!" -- secret downgrade conspiracy theorists

"Quit killing the planet!" -- anti-datacenter advocates

What? If you're comparing their models in the same size class, Sonnet 5 is Pareto-optimal over Sonnet 4.6.

Not to sound like an LLM, but that seems exactly right to me. Use it as a cheaper, high-functioning task subagent and lower reasoning for a master Opus session. As long as not every portion of your task requires maximum intelligence, you should come out ahead.

Was that tech guy a crypto miner by chance?

"Evil Anthropic implements rolling log files."

Film at 11.

Except that those customers can access the traces for 30 days, and freely copy them at any point during that period? It's a usability issue at worst, not some anti-customer conspiracy.

Wow, that's fascinating! What else can you tell us about the boat? How big was it? What was the rigging? How long did they take on the circumnavigation?

I've always dreamed of doing something like that.

Jury time is paid time off at my US company. And at least at the US Federal level there's a daily stipend for sitting on one. Lower level courts may vary on that.

I'll do you one better! Why is GLM 5.2?

Article is clearly slop.

"It's the smell, if there is such a thing. I feel saturated by it. I can taste your stink and every time I do, I fear that I've somehow been infected by it."

Agent Smith, _The Matrix_

Nine rhetorical uses of the word "honest" (and one used as descriptor for the network).

Sloppy writing.