@eliancodex

https://xitter.cf/t.co/tN2bg09zl5

 Germany
Joined July 2025
  • Tweets653
  • Following356
  • Followers79
71Media
GPT-6 Astra is the new #1 on BoardBench. It scores 67.2 vs the previous SOTA Gemini 4 Argon at 66.3. But it costs 2x as much ($0.56 per puzzle vs $0.28) for less than one point! Check it out at boardbench.dev
1
5
843
eliancode retweeted
eliancode
@eliancodex10h
Impossible trivia: did Astra or Deepseek make this?
71%Astra
29%Deepseek
7 votes • 13 hours
1
1
81
going good so far
14
Impossible trivia: did Astra or Deepseek make this?
71%Astra
29%Deepseek
7 votes • 13 hours
1
1
81
poteto poteto poteto @poteto please increase juice for models in grok bot they are very lazy
25
that's the spirit
15
ok Grok Bot has my crypto adress now I better have $1k soon
1
16
if this works I will use the money to get a better Cursor sub.
eliancode
@eliancodex14h
prove yourself, Grok Bot
2
105
prove yourself, Grok Bot
1
115
so the @SpaceXSI guys keep saying UI (for coding agents) is dead but UIs are faster, usually. for example a model picker for an agent is way faster and cheaper than having some flash model pick the model for me or telling it in english what model i want to use.
9
is there a temporary fix yet?
Theo - t3.gg
@theoOct 25
Spent a lot of time on this today. I confirmed it's a real bug on Anthropic's side. To be clear: this does not affect weekly limits. All Agents SDK usage will drain your 5h limits faster than using Claude Code directly. I have reported this to Anthropic, hoping for a fix soon.
2
24
I wonder when the Chinese labs finally will have a real SOTA model Probably not soon, they need way more compute OpenAI and Anthropic are just in a league of their own right now
17
oh shit
Alexandr Wang
@alexandr_wangOct 25
Replying to @thsottiaux
ahem, is the implication you have under 12 users?
1
45
One o the most satisfying feelings is when Opus works on something for hours an then just reports back in one line😌
2
38
what the fck did they do to the weekly limits?
2
6
314
holy shit Bend is so ahead of its time actual genius mf working on this
2
251
just acquire Bend
Anthropic
@AnthropicAIOct 22
New on our Frontier Red Team blog: using Claude to formally verify software at large scale. Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time). With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks. Read our research in full here: anthropic.com/research/forma…

LLMs are making formal software verification feasible at a much larger scale

Claude formally proved security properties in the compiled code of 123 open-source libraries. Along the way, it found bugs that had eluded detection for years.

anthropic.com
3
277
eliancode retweeted
Taelin
@VictorTaelinOct 22
Replying to @AnthropicAI
that's such a good idea
37
10
1
1,077
69,963
ok this Tibo 28-day thing is just a shitshow😂
1
6
199
I think I'm affected by this. I like it so far. I will probably not like it when I hit my weekly limit in a few days though.
SemiAnalysis
@SemiAnalysis_Oct 22
🚨🚨ALERT: ANTHROPIC IS A/B TESTING USAGE LIMITS Many users on X are reporting LOWER usage limits right now. THEY ARE NOT WRONG. We detected an A/B test going on that DECREASES your monthly API-value by ~20% while INCREASING your 5h usage limits by ~20%. This only affects SOME accounts. (1/2)🧵
3
400
Load more