981–990 of 1001 posts
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…
So my pipeline is mostly stuck with: (1) brainstorm with Gemini (2) plan with GPT (3) augment the plan with Gemini (4) execute the plan with Opus.
Perhaps, given all the materials filtered and prepared, Opus is good for verification.
This made me laugh. Training Opus 4.7 on business skills caused it to sometimes exhibit dishonest behaviour, and not training 4.8 on those skills removed it. From the system card: > 6.2.5 External testing from Andon Labs Andon Labs reviewed the behavior of Claude Opus 4.8 in their simulated Vending-Bench 2 retail-management evaluation, as reported in the Capabilities section of this system card (see Section 8.13.5).…
Earlier quoted context omitted.
I've been tasking LLMs to write a traditional AI for a full vibe-coded RTS. I remove the human players and let them battle. I don't know why but I enjoy watching AI players battle so much :) In the repo, I even have a tournament script that calculates ELOs. So far, codex was unmatched. I'll try with Opus 4.8 too. https://egeozcan.github.io/unnamed_rts/game/ https://github.com/egeozcan/unnamed_rts/blob/main/src/script…
I'm happy to report that this game is very fun for natural intelligence entities too. :)
I use 4.6, because 4.7 is super lazy, deflects responsibility, and assumes it is good and I am bad, and avoids checking reality. It looks like it's trained on lazy humans instead of good engineers. Should I try 4.8? I am happy with 4.6. I am not happy with 4.7.
Every time I tell Claude to review a git changeset for performance or security issues, it just starts doing random stuff:
test -f /tmp/aaa.txt && echo "AAA-EXISTS"; test -f /tmp/bbb.txt && echo "BBB-EXISTS"; head -c 5 /tmp/aaa.txt > /dev/null && echo "READ-OK") ⎿ AAA-EXISTS BBB-EXISTS READ-OK
Was about to split my $200 max plan into $100 Claude and $100 codex, let’s see if I still need to