bolly (@userbolly) header
bolly (@userbolly) profile picture
Atlanta, GA
Joined December 2022
Photo by bolly (@userbolly)
bolly retweeted
Real life, baby
19,270
96,485
45,725
776,822
98,604,849
bolly retweeted
Never stopped gaming... just changed the games.
8
23
2
275
7,874
mark my words something changed at anthropic not sure if leadership shakeup new policies or just some internal plan but something changed
Claude.dev is our new home for developers building with Claude. You'll find engineering deep dives, Claude Code and API guides, tips from the teams building Claude, and some fun easter eggs.
32
6
1
421
163,006
twitter users are living 6 months ahead of everyone else when it comes to AI
297
530
106
10,672
186,121
bolly retweeted
Resets all propagated. That will be all. Have a fantastic weekend.
2,107
469
559
16,115
2,593,170
WE ARE COOKING!! Three of @openclaw’s four biggest weeks for npm downloads have been this September. Thank you to everyone sharing feedback and to all our community contributors making this possible!
13
20
3
118
48,576
Opus 5.5 is really bad it ruins your sleep because it’s so fun to use and it barely drains your usage limits please fix this
What is Opus 5.5 bad at? Anyone find its limitations yet? It’s crushed everything I’ve thrown at it.
69
55
7
2,186
74,881
Opus 5.5 is way, way, way better than Opus 5. Sorry about that model, please try this one.
323
315
170
11,120
1,104,737
bolly retweeted
Been pushing Opus 5.5 hard all day and it's barely making a dent on my usage limits. Impressive!
195
93
28
6,868
200,072
claude is back.
3
56
bolly retweeted
Just cancelled my Codex subscription. Going back to Claude. Opus 5.5 was enough to convince me to switch back. It mogs GPT-6 Astra. Easy decision.
143
34
13
1,613
92,591
bolly retweeted
Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.
2,224
5,252
3,053
53,190
10,205,716
bolly retweeted
One more thing: we’re increasing five-hour usage limits on Pro, Max, and Team plans. We’re also providing subscription users a rate limit reset, which you can save and use whenever you choose.
544
804
925
15,040
2,683,689
Opus 5.5 performs at the level of Fable 5.1. It's ~30% faster and ~40% cheaper than Opus 5 per task. In Claude Code: - 5-hour session limits increase 20% today - Opus 5.5 is priced lower, so it goes 25% further within limits - Pro, Max, and Team users get a reset to use anytime
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
465
1,203
553
16,242
1,555,884
bolly retweeted
ngl 90 percent of us burned the Codex Usage Yesterday. In hope of the Reset and it is almost evening and we still refreshing the page. Is this a Joke?
Ladies and gentlemen... start... your... ENGINES. We are almost Tuesday and I promised a reset for Tuesday. Among some other things. See you soon.
103
15
3
935
111,842
Replying to @openclaw @steipete
Update went flawless chat 🔥🔥🔥🚀
1
2
979
ok the stack is clear macbook + mac mini 1) Cursor 2) Codex 3) Grok Bot 4) Native Apps built custom this is how you win long term.
53
13
3
486
40,387
GPT-Live-1 is now available in the API. Bring ChatGPT’s natural back-and-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose.
566
1,460
976
18,039
7,455,519
bolly retweeted
This is GPT-6 Astra. Anything you can do on a computer, Astra can do for you. Fast.
9,134
35,195
26,598
338,670
138,958,639
bolly retweeted
There are levels of vibe coding.
571
3,692
360
77,770
1,316,784