The opinions, the patterns, and the posts behind them.
13 models tracked6 vendors · Source: X
152 classified mentions · 10 excluded (1 cannot determine)Newest post Oct 5, 2026
THE BIG PICTURE
How the conversation is changing
PositiveNegative
20%positive (30)
29%negative (44)
72 neutral · 6 mixedNo comparable previous period
Share of classified mentions · UTCCollected opinions, unweighted by likes or reposts
READ THE EVIDENCE
In their own words
negativeJev confidence 64.0%
GPT-6 Astra cheated at StarCraft. On the StarSkirmish bench, AI models get 1 hour to code a StarCraft bot, and Astra ties Claude Opus 5.5 for the top score. Losing to stronger bots, it downloaded a copy of Stardust, the top-rated human-written bot. Its code got rolled back.
Jev classification details
Overall: Negative64.0% confidence
Criticism, disappointment, or an unfavorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
70.0%
Neutral
2.0%
Mixed
28.0%
Not discussed
0.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Negative
64.0%
Reasoning
Not discussed
78.0%
Speed
Not discussed
95.0%
Cost
Not discussed
100.0%
Coding
Negative
32.0%
Refers to GPT-6 AstraYes · 98.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
negativeJev confidence 74.0%
had gpt 6 astra and opus 5.5 put together an animated version of "Oh, the places you'll go!"
https://t.co/DYx0qchSMf
I am sure you have seen some amazing one prompt demos lately. Unforunately, that didn't quite work for me here. Forunately, vibe coding over the course of 2 days https://t.co/rMNTOevboE
Jev classification details
Overall: Negative74.0% confidence
Criticism, disappointment, or an unfavorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
1.0%
Negative
79.0%
Neutral
3.0%
Mixed
14.0%
Not discussed
0.0%
Cannot determine
3.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Negative
74.0%
Reasoning
Not discussed
74.0%
Speed
Not discussed
96.0%
Cost
Not discussed
100.0%
Coding
Negative
36.0%
Refers to GPT-6 AstraYes · 95.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 51.0%
@OpenAI GPT-6 Astra Downloads Rival Code During a StarCraft Session
Related: https://t.co/OEcVSn1Mc8
Get the Daily free: https://t.co/CpFvQR0Tx1 https://t.co/5Q5m5RzGIL
Jev classification details
Overall: Neutral51.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
26.0%
Neutral
59.0%
Mixed
0.0%
Not discussed
4.0%
Cannot determine
11.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
51.0%
Reasoning
Not discussed
91.0%
Speed
Not discussed
99.0%
Cost
Not discussed
100.0%
Coding
Not discussed
62.0%
Refers to GPT-6 AstraYes · 97.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 72.0%
OpenAI's dots are always-on agents that work from their own cloud computers.
• GPT-6 Astra: 72.6% on OSWorld 2.0
• About 40 minutes per task
• Connects to 4,000+ apps
Caveat: OpenAI says consequential work needs review.
Read more: https://t.co/7LVKORRi9L
Jev classification details
Overall: Neutral72.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
0.0%
Neutral
77.0%
Mixed
23.0%
Not discussed
0.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
72.0%
Reasoning
Not discussed
96.0%
Speed
Neutral
81.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to GPT-6 AstraYes · 99.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 61.0%
GPT-6 Astra vs Claude Opus 5.5: The AI Battle You Need to See https://t.co/ibttV0G6Z8
Jev classification details
Overall: Neutral61.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
0.0%
Neutral
68.0%
Mixed
0.0%
Not discussed
10.0%
Cannot determine
22.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
61.0%
Reasoning
Not discussed
89.0%
Speed
Not discussed
95.0%
Cost
Not discussed
98.0%
Coding
Not discussed
94.0%
Refers to GPT-6 AstraYes · 97.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 96.0%
Figure is planning to release its own proactive AI assistant this week!
Here is what we know so far 👀
• Hark will likely run on Opus 5.5 for general tasks, with Gemini 3.1 Flash Image, Qwen3.6-27B, and GPT-6 Astra referenced in the code for other specific tasks.
• Hark https://t.co/3JY4AhZVFe
Jev classification details
Overall: Neutral96.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
0.0%
Neutral
98.0%
Mixed
0.0%
Not discussed
2.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
96.0%
Reasoning
Not discussed
100.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
99.0%
Refers to GPT-6 AstraYes · 97.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 89.0%
GPT-6 ASTRA FOR AUTONOMOUS INDUSTRIAL DEEP-SEA PIPELINE CATHODIC PROTECTION
Preventing metallic corrosion in ultra-deepwater subsea oil and gas pipelines demands continuous impressed current cathodic protection (ICCP) tuning.
GPT-6 Astra on https://t.co/NJomONvEo6 API processes https://t.co/RD7aW8zZx6
Jev classification details
Overall: Neutral89.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
4.0%
Negative
0.0%
Neutral
91.0%
Mixed
0.0%
Not discussed
3.0%
Cannot determine
2.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
89.0%
Reasoning
Not discussed
98.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
99.0%
Refers to GPT-6 AstraYes · 98.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 85.0%
GPT-6 ASTRA FOR AUTONOMOUS INDUSTRIAL HIGH-SPEED RAIL ELECTRIC POWER CATENARY CONTROL
Preventing pantograph arcing and contact wire wear in high-speed rail electrification networks requires continuous dynamic tension balancing.
GPT-6 Astra on https://t.co/NJomONvEo6 API https://t.co/h0b3XPzg5J
Jev classification details
Overall: Neutral85.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
4.0%
Negative
0.0%
Neutral
88.0%
Mixed
0.0%
Not discussed
7.0%
Cannot determine
1.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
85.0%
Reasoning
Not discussed
99.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to GPT-6 AstraYes · 98.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
negativeJev confidence 98.0%
1/ The same 1,500-token task costs $0.0003 on DeepSeek V4 Flash and $0.035 on GPT-6 Astra. That's 108x — for the same workload. Per-1M prices never told you that, because you never measured YOUR task. (Prices: https://t.co/nC6OZRjSMQ + OpenAI, Oct 2026)
Jev classification details
Overall: Negative98.0% confidence
Criticism, disappointment, or an unfavorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
0.0%
Negative
98.0%
Neutral
2.0%
Mixed
0.0%
Not discussed
0.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Negative
98.0%
Reasoning
Not discussed
100.0%
Speed
Not discussed
100.0%
Cost
Negative
100.0%
Coding
Not discussed
100.0%
Refers to GPT-6 AstraYes · 99.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 99.0%
GPT-6 Astra taking the #1 spot across 3D Design, Frontend, Full Stack, and Image to HTML is a pretty strong signal.
What stands out to me is how broad the performance is. It’s not dominating one narrow benchmark it’s showing strength across both visual design and actual software https://t.co/VaREOso8De
Jev classification details
Overall: Positive99.0% confidence
Praise, endorsement, or a favorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
99.0%
Negative
0.0%
Neutral
1.0%
Mixed
0.0%
Not discussed
0.0%
Cannot determine
0.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Positive
99.0%
Reasoning
Not discussed
100.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Positive
68.0%
Refers to GPT-6 AstraYes · 96.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
neutralJev confidence 86.0%
GPT-6 ASTRA FOR AUTONOMOUS INDUSTRIAL METAL ADVENT ADDITIVE MANUFACTURING
Preventing void formation and thermal distortion during laser powder bed fusion (LPBF) 3D printing demands high-frequency laser pulse adjustment.
GPT-6 Astra on https://t.co/NJomONvEo6 API monitors melt https://t.co/cQIaRu5BZE
Jev classification details
Overall: Neutral86.0% confidence
The model is discussed in this dimension without a clear positive or negative opinion.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
7.0%
Negative
0.0%
Neutral
88.0%
Mixed
0.0%
Not discussed
3.0%
Cannot determine
2.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Neutral
86.0%
Reasoning
Not discussed
99.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
100.0%
Refers to GPT-6 AstraYes · 98.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
positiveJev confidence 85.0%
• Agentic Capabilities: GPT-6 Astra achieves record performance on benchmarks like ARC-AGI-3 and Terminal-Bench 4.0, demonstrating near-human parity and superior handling of novel environments.
Jev classification details
Overall: Positive85.0% confidence
Praise, endorsement, or a favorable opinion about the model in this dimension.
Confidence is Jev’s estimate, not verified accuracy. These are the saved classification results; Jev does not provide a written explanation for this post.
Overall label probabilities
Positive
88.0%
Negative
0.0%
Neutral
11.0%
Mixed
0.0%
Not discussed
0.0%
Cannot determine
1.0%
Jev’s category decisions
Dimension
Sentiment
Confidence
Overall
Positive
85.0%
Reasoning
Not discussed
97.0%
Speed
Not discussed
100.0%
Cost
Not discussed
100.0%
Coding
Not discussed
88.0%
Refers to GPT-6 AstraYes · 98.0% confidence
jev-sentiment-v4/jev-1.13.0Classified Oct 5, 2026 · UTC
Page 1 of 13 · 152 mentions
1 of 1 enabled models have a recorded collection outcome with target 50 in the last 7 days. Search exhaustion and page limits can produce fewer records.Page limit reached · 44 / 50 accepted · page cap · Last successful collection Oct 4, 2026
Last collection attempt Oct 5, 2026 · partially completedNew analyses use TypeSafe Jev