OpsConfig @OpsConfig

codeandstream.com A small farm in the mountains. Joined February 2013

Tweets

326
Followers

767
Following

6K
Likes

6K

OpsConfig @OpsConfig

18 hours ago

Comparing thinking tokens across models/providers is fraught, and of limited value. Different models, different backend implementations, different tokenizers, etc. Stronger models should be able to solve more complex problems using less thinking tokens/test time compute. The older pre-adaptive thinking Opus models are weaker so even with higher thinking token allocation their performance on chess doesn't improve enough to catchup to latest OpenAI models. With that said, I do think there is value in tracking reasoning/thinking token allocation to see how often low/zero thinking token allocation corresponds to poor performance.

0 0 0 11 0

View Details

OpsConfig @OpsConfig

18 hours ago

While regardless of chess performance Anthropic models have continued to get stronger in other domains, my own anecdotal experience was that Opus 4.5 and Opus 4.6 were the last Opus models to feel consistent. Ever since Opus 4.7 I feel like I am constantly having to correct and double-check the model's work. One moment the model feels smart, the next it is apologizing to me for the umpteenth time for having made a mistake. These days anytime I use an Anthropic model for any serious work I am constantly farming out adversarial reviews to codex/OpenAI models. This change in anecdotal vibes for me coincided with Anthropic's shift to "adaptive thinking". The older model's used the now deprecated "extended thinking" feature. If we add in data on the older model's we see a profile far closer to the OpenAI models as far as thinking token allocation. Adaptive thinking definitely saves money on a per API call basis, but I do wonder to what extent that comes at the cost of quality. 8/

1 0 0 18 0

View Details

OpsConfig @OpsConfig

18 hours ago

A few thoughts on why @AnthropicAI's Opus 5 sometimes felt lazy compared to @OpenAI 's models. I like to use chess as a benchmark/eval for AI models. It is a crude/toy benchmark, but it does a good job of giving a sense of when the frontier model's make leaps forward and helps temper some of the benchmaxxing. 1/

1 0 0 51 0

View Details

OpsConfig @OpsConfig

21 hours ago

Out of curiosity, I ran it through my standard chess eval gauntlet on low, medium, high, and max. It lost every game except one. Here is one of its losses, mate in 7 moves with stockfish at 1320. All match replays have been added to the library: codeandstream.com/chess/#g=sb_lo…

0 0 0 41 0

View Details

OpsConfig @OpsConfig

21 hours ago

Based on the tokenizer data the new stealth model "space-bunny-alpha" appears to likely be part of MiniMax lineage.

1 0 1 219 0

View Details

zeta @zeta_globin

a day ago

@GuiveAssadi @AnthropicAI there's a ton of enzymes similar to crispr, we've known this forever covered this in 2019 with @snuppydogg years ago and it's when I knew we'd be friends I think I need to delete twitter and make more money in the real world

2 5 98 7K 7

View Details

The Yale Review @yalereview

a week ago

Annie Dillard has died. In our Summer 1988 Issue, she wrote about the "surprising letters" and gifts that fans and readers sent her over the years—a fossil fish, a marriage proposal, a check for $2.50, and, again and again, questions about God. yalereview.org/article/annie-…

1 58 259 7K 85

View Details

The New York Times @nytimes

a week ago

Breaking News: Annie Dillard, the Pulitzer Prize-winning author of the modern classic “Pilgrim at Tinker Creek,” has died at 81. nyti.ms/4hrp9BD

47 251 1K 642K 274

View Details

Matthew Cooper @mattizcoop

2 weeks ago

A lovely @nytimes obit for my brother who died on Labor Day. Jonathan Cooper, Who Made Violins the Old-Fashioned Way, Dies at 76 nytimes.com/2026/09/12/art… via @nytimes

23 46 249 26K 11

View Details

Jim O'Shaughnessy @jposhaughnessy

2 weeks ago

❤️‍🩹

7 15 161 6K 1

View Details

Steven Strogatz @stevenstrogatz

2 weeks ago

Two heroes of today's Navier-Stokes story are not getting enough credit. Córdoba and Martínez-Zoroa came up with the crucial strategy. Others built on it and, with the help of AI, provided the computations that finished the problem. Thankfully @QuantaMagazine gets this right:

21 338 2K 90K 239

View Details

OpsConfig @OpsConfig

2 weeks ago

@markchen90 Just to make sure I understand are saying you aren't sure if they had these settings turned on/off, which seems quite reasonable? Or are you saying even if these settings are turned off there is still some gray area?

25 17 581 32K 42

View Details

OpsConfig @OpsConfig

2 weeks ago

As much fun as it is to have LLMs play against stockfish, sometimes it's nice to watch some 1v1 matches. Twenty games of GPT-6 Astra versus Fable 5.1 are now up on: codeandstream.com/chess