841–850 of 1001 posts
Now when will the innovation happen where say cost of running Haiku performs level of Opus 4.5?
I feel models are only getting bigger instead of models becoming more efficient and cheaper to run
A rambling comment: I think this is the first time we've had a third minor version bump on a frontier Anthropic model. (I count the 0.5s as major here, because they've been issued non-sequentially and also corresponded to massive capability leaps, eg, Sonnet 3.5, Opus 4.5). So now the Opus 4.5 family has successors 4.6, 4.7, and 4.8, each posting fairly modest claimed gains. My own experience w/ 4.6 and 4.7 are that…
May be my tasks are rudimentary but the results I get with the 4.5 model are just the same as 4.7 or 4.6. it's just at the advanced models consume more tokens and and are actually loss making for my work. The incremental changes that they are making are not really that valuable. In fact I have found that even glm 5.1 is giving me something equivalent to what Opus 4.6 gives. Am I missing something that everyone else i…
I thinks there's a big push to get these companies in a state where they can be dumped on public markets.
Earlier quoted context omitted.
It almost appears as if the code was minified. The variable names are short and formatting looks like it's written to minimize whitespace. Did it write it in this compact format all on it's own?
Yeah looks extremely compact. I didn't instruct it or told it to use as few lines of code or characters or nothing of the sort. Not sure why it did that. Its own rationale (which is highly suspect, but the only lead I have) is that it defaults to dense style if it has to write a file in a single go. May be a kernel of truth somewhere in there.
Today I was a few hours into chasing down a very tricky timing-dependent bug with GPT 5.5 and we were starting to go into circles. I noticed Opus 4.8 had showed up in GitHub Copilot so I switched over and pointed it at my notes so far. Another hour of steady progress and it tracked it down to some missing synchronisation in an upstream library which was occasionally corrupting a linked list. N=1 but worth every one o…
I do notice this tendency for 5.5 to go in endless circles.