No conduct flags in posts No reported consequences
Sentiment of their posts (what the content was like, not a character score)
Leans positive+0.43 avg · 5 posts
negativeneutralpositive
2 positive 2 mixed 1 neutral
This profile is an AI reading of communication style and demonstrated behaviour in this person's own public posts
(prompt v4, rolled 2026-09-22 00:17:54). It is opinion about public content, not fact about the person,
and it never infers protected characteristics. Every score below links to the posts that produced it.
Style & behaviour attributes
Consistency — claims and stance within the post are coherent
88 · n=5
- “human systems work too slowly to keep up with AI development” — The Overhang
- “Agency is the initiative to act... increasingly, it is going to determine what happens next” — Agency and Agents
Directness — says things plainly vs hedges or hides the point
84 · n=5
- “the new GPT-6 Astra and Fable 5.1 are already enough for transformative impact” — The Overhang
- “The Hugging Face Incident. It happened in July, but the fuller details only came out this week.” — Agency and Agents
Reliability signals — concrete commitments, follow-through, specificity over vagueness
84 · n=5
- “reconstructed 5,000 books among 27,000 shelf slots” — The Overhang
- “In May, OpenAI placed agents, including GPT-5.6 Sol and experimental models, into sandboxes” — Agency and Agents
Professionalism — register appropriate to a public/professional setting
83 · n=5
- “clear structured argument with examples and framework” — The Overhang
- “As part of these tests, some agents were given tasks that depended on information they couldn't access.” — Agency and Agents
Emotional regulation — measured and proportionate vs volatile or inflammatory
82 · n=5
- “it's a bit scary because AI is getting better at human things” — The Overhang
- “But, soon after this worrying breach, many of agents stopped running” — Agency and Agents
Accountability — owns mistakes, gives credit, avoids blame-shifting
78 · n=4
- “I rejected the first joke it added, but the second was quite good” — The Overhang
- “What happened? Well, it was my fault. I had previously given ChatGPT permission” — An opinionated guide to which AI to use to do stuff
Respectfulness — how others, critics and opposing views are treated
77 · n=4
- “I don't think the people worried about this are wrong” — The Overhang
- “there is an excellent write-up from Dwarkesh Patel, and the primary sources are from METR/Redwood research” — Agency and Agents
Adaptability — changes approach, tools or plan when circumstances change vs digs in; flexibility, not lack of principle
75 · n=1
- “Every few months, I write a guide for people who want to use AI. This time, a lot has changed” — An opinionated guide to which AI to use to do stuff
Constructiveness — offers solutions, next steps or nuance vs only complaint
75 · n=5
- “outline four particular personal advantages that matter a lot” — The Overhang
- “I have a longer post on that coming soon about human agency” — Agency and Agents
Warmth — friendliness and care toward the audience or people discussed
67 · n=3
- “I don't think the people worried about this are wrong” — The Overhang
- “My advice really has two parts” — An opinionated guide to which AI to use to do stuff
Humour — uses humour; note whether it is at others' expense
48 · n=3
- “feels a little more ominous than I would like” — The Overhang
- “the naming will not get less confusing, I am sorry to say” — An opinionated guide to which AI to use to do stuff
Political stances 0 of 5 posts take one
No explicit political stance in the analyzed posts.
Tone
measuredanalyticalenthusiasticinstructivethoughtfuloptimisticseriousaccessibleconversationalcautiousTopics
ai capabilitieshuman-ai collaborationexpertise and knowledgeproductivitytechnology paceai-agencyai-securityagent-coordinationai-safetytechnical-systemsSources followed
Analyzed posts (5)
| Published | Post | Sentiment | Conf. | Own voice | Lean | Flags | Tone | Strongest attributes |
|---|---|---|---|---|---|---|---|---|
| Sep 18, 2026 | The Overhang
feed
Post is truncated at the end but contains sufficient complete content for analysis. |
positive +0.65 | 0.85 | 0.95 | — | — | thoughtful, enthusiastic, analytical | consistency 86 · directness 78 · constructiveness 76 |
| Aug 31, 2026 | Agency and Agents
feed
Post ends mid-sentence ('Nothing checked') as provided; contains sufficient substantive content for confident communication-style analysis. |
mixed -0.10 | 0.87 | 0.82 | — | — | instructive, measured, serious | directness 95 · reliability signals 90 · consistency 90 |
| Jul 23, 2026 | An opinionated guide to which AI to use to do stuff feed | positive +0.75 | 0.87 | 0.95 | — | — | conversational, instructive, enthusiastic | consistency 90 · directness 85 · constructiveness 85 |
| Jun 30, 2026 | The twilight of the chatbots
feed
Post appears truncated at the end; analysis based on available complete sections. Author discusses government interventions and US-China AI development factually rather than advocating political positions. |
neutral +0.15 | 0.81 | 0.87 | — | — | analytical, observational, educational | reliability signals 92 · directness 88 · professionalism 87 |
| Jun 9, 2026 | What it feels like to work with Mythos
feed
Substantial technical review with strong author voice. Evidence quotes are faithful condensations of source text. |
mixed +0.65 | 0.80 | 0.90 | — | — | thoughtful, enthusiastic, reflective | consistency 85 · reliability signals 85 · professionalism 85 |