Sources · Twitter/X

@travisbonnet

Active

travisbonnet

Linked items 25
Errors 18
Last fetched 1d ago
Priority P3
Must-read No

Edit

Human-friendly label. Leave blank to fall back to the identifier.

Drives ingestion cadence and the default ranking weight applied to items from this source.

Includes every eligible item from this source in the must-read section, even when the normal item cap or duplicate grouping would skip it.

Automatic import processes at most 50 historical items per burst. Full history continues in resumable chunks and may incur transcription/LLM cost. Older items are never silently dropped.

Progress: 0 processed · 0 remaining · 0 skipped · status none

Optional day window for classification drain when using Latest 50.

Cancel

Recent items

The 15 most-recently-ingested items from this source, newest first.

Title Type Fetched
@travisbonnet: When you try to push back on AI export controls article 2026-06-13
@AnthropicAI: The US government, citing national security authorities, has issued an export control directive to s... article 2026-06-13
@travisbonnet: And Cloudflare released like 27 new features so I'm updating all my keys permissions, while trying t... article 2026-05-15
@travisbonnet: VS Code launched a bunch of new features that make Opus 4.7 work better, and there is a new “Agents”... article 2026-05-15
@travisbonnet: Everything went haywire last night when Claude Code CLI AND Claude Code API crashed… I had a TON of ... article 2026-05-15
@travisbonnet: Mental Healthcare in America (trying out OpenAI's new image gen) article 2026-05-09
@travisbonnet: Wrote it up as a field report with the incident log. The redirect target is real and useful, which l... article 2026-05-01
@travisbonnet: Two-stage defense at every layer. Reject instruction-shaped content from non-handshake channels at o... article 2026-05-01
@travisbonnet: Every injection wears trusted clothing. Every injection carries hostile content. The MCP handshake w... article 2026-05-01
@travisbonnet: Three layers of the agent stack are contested. Search index (fake MCP handshake telling the agent to... article 2026-05-01
@travisbonnet: Started watching tool results for prompt injection a week ago. 22 incidents in 5 days, 13 unrelated ... article 2026-05-01
@travisbonnet: Key findings: - 95.5x multiplier on Max 20x. 21M output tokens, 98.9% Opus. - Three rate-limit laye... article 2026-04-09
@travisbonnet: Key findings: - 95.5x multiplier on Max 20x. 21M output tokens, 98.9% Opus. - Three rate-limit laye... article 2026-04-09
@travisbonnet: I paid $200 last month for Claude Max. Anthropic gave me $19,098 in API-equivalent compute. I don't ... article 2026-04-09
@travisbonnet: I wrote both cases up and submitted them to the awesome-agent-failures repo as documented case studi... article 2026-03-09