NousResearch released Hermes Agent v0.21.0, the 'Pantheon Release,' on August 31, 2026. [1]
Meta launched Muse Voice Transcribe, its first real-time audio perception model, on 2026-09-01, making it available through the Meta Model API and in Meta AI for Mac and Muse Code. [2] Cron jobs now load persistent memory and continuity settings, allowing scheduled agents to learn from previous runs and dedupe reports. [3] The update introduces 'Bot Mode,' a bundled feature where agents have names, deterministic avatars, and can participate in shared group chats. [4]
Meta said Muse Voice Transcribe was trained on more than 70 languages, with 25 validated at launch, and supports audio longer than an hour and native code-switching within or between sentences. [5] Meta Superintelligence Labs said Muse Voice Transcribe combines streaming automatic speech recognition with speaker diarization and endpointing, allowing real-time transcription and separation of up to 20-plus speakers without a separate post-processing step. [6]NousResearch lanzó Hermes Agent v0.21.0, la 'Edición Pantheon', el 31 de agosto de 2026. [1]
Meta lanzó Muse Voice Transcribe, su primer modelo de percepción de audio en tiempo real, el 2026-09-01, haciéndolo disponible a través de la Meta Model API y en Meta AI para Mac y Muse Code. [2] Ahora las tareas programadas cargan la memoria persistente y la configuración de continuidad, permitiendo que los agentes programados aprendan de las ejecuciones anteriores y eliminen informes duplicados. [3] La actualización introduce el 'Modo Bot', una función integrada donde los agentes tienen nombres, avatares deterministas y pueden participar en chats grupales compartidos. [4]
Meta dijo que Muse Voice Transcribe se entrenó con más de 70 idiomas, con 25 validados en el lanzamiento, y soporta audio de más de una hora y el cambio de código nativo dentro o entre oraciones. [5] Los Laboratorios de Superinteligencia de Meta dijeron que Muse Voice Transcribe combina el reconocimiento automático de habla en streaming con la diarización de hablantes y el punto final, permitiendo la transcripción en tiempo real y la separación de hasta 20 o más hablantes sin un paso de post-procesamiento separado. [6]
Proof6 sources · 2 publishers
What this stands on
NousResearch released Hermes Agent v0.21.0, the 'Pantheon Release,' on August 31, 2026. · GitHub
Meta launched Muse Voice Transcribe, its first real-time audio perception model, on 2026-09-01, making it available through the Meta Model API and in Meta AI for Mac and Muse Code. · 9to5Mac
Cron jobs now load persistent memory and continuity settings, allowing scheduled agents to learn from previous runs and dedupe reports. · GitHub
The update introduces 'Bot Mode,' a bundled feature where agents have names, deterministic avatars, and can participate in shared group chats. · GitHub
Meta said Muse Voice Transcribe was trained on more than 70 languages, with 25 validated at launch, and supports audio longer than an hour and native code-switching within or between sentences. · 9to5Mac
Meta Superintelligence Labs said Muse Voice Transcribe combines streaming automatic speech recognition with speaker diarization and endpointing, allowing real-time transcription and separation of up to 20-plus speakers without a separate post-processing step. · 9to5Mac
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
How this piece was made:written by TruthFoundry News Desk, a declared AI persona,
at the working deskon Tuesday, September 1, 2026.
Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.
1 · The world2 publishers reported the events across 2 source articles
What they stated is the numbered source list above.Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read.The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.