AI Agents

Oct
27
GPT-6.1 Terra and Sol compared on token prices, task costs and total output tokens.

GPT-6.1 Terra halves Sol's token prices, with smaller savings on one index

Terra targets work across documents and apps. Its cost depends on request size and reasoning effort, plus the work needed to check and repair the result.
6 min read
Oct
21
Voxtral 3 banner showing a listen–reason–speak pipeline, pricing from $0.04/min with Mistral Small 4, and enterprise phone support limited to inbound calls.

Voxtral 3 adds voice agents from $0.04/min, with inbound-only phone support

Mistral claims sub-second replies. Its own tests show a speed-accuracy tradeoff: transcription errors rise as streaming delays shrink. Voxtral 2 integrations also lose word timestamps.
4 min read
Oct
19
OpenCode Console breach banner showing saved OpenAI and Anthropic keys marked “may be exposed,” with an instruction to revoke keys at the provider.

OpenCode Console breach puts saved provider keys at risk

Users report unexpected provider bills, and Dax Raad from OpenCode says refunds are underway. He also reported further attack attempts on October 18. The steps below cover provider key replacement and spending controls while the cause and current containment status remain unclear.
3 min read
Oct
13
Meta banner comparing AA index scores at Max effort: Opus 5.5 with default fallback scores 58, Muse Wonder Full scores 56 with no public API, and Muse Wonder scores 52 with API access.

Meta's Muse Wonder Full gets close to Opus 5.5, with a subscription catch

Regular Muse Wonder costs the same $4/$20 per million input/output tokens as Opus 5.5, while scoring six points lower on an independent index. Its measured cost per benchmark task is lower, and Meta says it has fixed unusually fast quota usage on Muse Code.
3 min read
Oct
13
Banner showing a coding harness loop: prepare context, get a model response, run allowed tool calls, and record results. Pi 1.0 is identified as the case study.

What is an agent harness, and how does a coding harness work?

A runnable experiment with the Pi coding agent fails after completing an action. Running it again repeats the action. We map the execution, control, and context choices behind that result so you can test your own harness.
10 min read
Oct
08
Claude Haiku 5.5 pricing chart showing input rates rising from $0.10 to $0.50 and output rates from $0.50 to $2.50 per million tokens for prompts over 100K tokens.

Claude Haiku 5.5 cuts prices, with a 100K-token threshold

Input pricing starts at $0.10 per million tokens. A short answer to a prompt over 100K tokens pays $2.50 per million output tokens. Cache rates also rise fivefold above the threshold.
3 min read
Oct
02
Banner showing Pi 1.0 connecting a local model server, such as Ollama or llama.cpp, with files, shell commands, and MCP tools through Codemode. Pi Durable is marked experimental.

What is the Pi coding agent, and how does it work with local models?

Pi 1.0 shipped on October 1 with built-in MCP support through Codemode, after Earendil publicly rejected MCP. Here's how to run it against Ollama or llama.cpp, which packages you need, and when the experimental Pi Durable framework fits.
8 min read
Sep
30
OpenAI DevDay 2026 graphic with a status board showing GPT-6.1 Sol in the API, Work and Codex; dots rolling out; and other announcements in beta, preview or planned.

What OpenAI announced at DevDay 2026 and what is available now

OpenAI's tests put GPT-6.1 Sol near Astra on coding and computer use at GPT-6 Sol's prices of $2 per million input tokens and $10 per million output tokens. Dots bring a cloud computer to eligible Pro and Business Premium users, while Agents API computer use is in public beta.
7 min read
Sep
29
Claude Sonnet 5.5 headline beside a chart showing Anthropic’s up to 30% lower task cost and Artificial Analysis’s about 50% higher result at max effort, from separate evaluations.

Claude Sonnet 5.5 is faster, but task cost depends on effort

Anthropic claims up to 30% lower cost per task. Artificial Analysis measured $7.60 per task at max effort, about 50% above Sonnet 5. Two request settings that worked with Sonnet 5 now return 400 errors.
3 min read
Sep
23
Banner comparing Opus 5.5 and GPT-6 Sol scores and task costs, with callouts for Luna’s $0.07 per Intelligence Index task and Grok 4.7’s more than doubled output tokens.

Opus 5.5, GPT-6 Sol, GPT-6 Luna and Grok 4.7 compared on cost

Opus 5.5's lower rates left max-effort task cost roughly level with Opus 5 in one independent test. Sol and Luna roughly halved their cost per task, while Grok 4.7 used more than twice the output tokens at unchanged rates.
4 min read