@eliancodex

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

 Germany
Joined July 2025
  • Tweets660
  • Following368
  • Followers81
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
850
which is superior for videos?
33%llms
0%world models
67%video models
6 votes • 1 days
1
176
opus 5.5, fable 5.1 and gpt-6 astra are the only decent coding models rn
1
2
394
if i see one more person on my tl that says that oais eth proof is p=np im gonna block them
11
nice
Bun
@bunjavascriptOct 27
claude.ai switched from TypeScript 7 to `bun check` type-checking got 69s faster
claude.ai CI typecheck: tsc → bun check 69 S faster 21s bun check 77% less time 4.3x faster tsc 90 s median time to type-check all of claude.ai in Cl • tsc is TypeScript 7 (native) • Oct 2026

ALT claude.ai CI typecheck: tsc → bun check 69 S faster 21s bun check 77% less time 4.3x faster tsc 90 s median time to type-check all of claude.ai in Cl • tsc is TypeScript 7 (native) • Oct 2026

25
POV: It's 2027 and Fable 6 just dropped and OpenAI tries to get you to use Terra😂
14
I encourage you to tell Opus to explain in 1 sentence once in a while. It's very relieving.
11
Wrong. Deepseek made it.
eliancode
@eliancodexOct 25
Impossible trivia: did Astra or Deepseek make this?
71%Astra
29%Deepseek
7 votes • Final results
1
4
429
eliancode retweeted
eliancode
@eliancodexOct 25
Impossible trivia: did Astra or Deepseek make this?
71%Astra
29%Deepseek
7 votes • Final results
1
1
1
532
going good so far
16
Impossible trivia: did Astra or Deepseek make this?
71%Astra
29%Deepseek
7 votes • Final results
1
1
1
532
poteto poteto poteto @poteto please increase juice for models in grok bot they are very lazy
27
that's the spirit
18
ok Grok Bot has my crypto adress now I better have $1k soon
1
17
if this works I will use the money to get a better Cursor sub.
eliancode
@eliancodexOct 25
prove yourself, Grok Bot
2
107
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.
10
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
28
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
1
18
oh shit
Alexandr Wang
@alexandr_wangOct 25
Replying to @thsottiaux
ahem, is the implication you have under 12 users?
1
48
One o the most satisfying feelings is when Opus works on something for hours an then just reports back in one line😌
2
40
Load more