Fresh stories
Condense.chat opens Adeline 1 proxy for 9% agent-loop compaction
Condense.chat opened a compression proxy that strips tokens with Helene 1 and compacts settled agent loops with Adeline 1 to about 9% of their size. The service claims 100M saved tokens and 3× plan extension for Claude or Codex users, so test it on non-sensitive workflows first.
Fable 5 users report Opus 4.8 fallbacks, refusals, and $321 sessions
Users posted mixed reports after Anthropic brought Fable 5 back: some sessions stayed on Fable, while others routed most work to Opus 4.8 or stalled mid-run. Watch for routing changes and cost spikes, since reports also mention refusals on ordinary tasks and ad hoc multi-model workarounds.
Hermes Agent updates web extraction with 60x faster reads and 49x lower cost
Nous updated Hermes Agent web extraction to skip the old summarizer loop, pass cleaner content directly to the model, and page large documents on demand. The change is claimed to cut read latency by up to 60x and cost by 49x, so teams should compare output quality before adopting it.
Codex app reportedly leaks GPT-5.6 Sol, Terra, and Luna model names
Codex app code now references GPT-5.6 Sol, Terra, and Luna, while posts claim Sol Ultra reaches 91.9% on TerminalBench at lower cost. Treat release timing, limits, and benchmark claims as unofficial until OpenAI publishes details.
Condense.chat opens Adeline 1 proxy for 9% agent-loop compaction
Condense.chat opened a compression proxy that strips tokens with Helene 1 and compacts settled agent loops with Adeline 1 to about 9% of their size. The service claims 100M saved tokens and 3× plan extension for Claude or Codex users, so test it on non-sensitive workflows first.
Fable 5 users report Opus 4.8 fallbacks and $600 Max quota rotations
Fable 5 users reported Opus 4.8 fallbacks, $600 Max-account rotations, slow browser automation, and token-saving subagents. Watch routing opacity, quota burn, and latency before relying on it for long-running agent work.
Claude Sonnet 5 ranks #3 on Vals and hits 183 turns on AA-Briefcase
Vals and Artificial Analysis published independent Sonnet 5 results a day after launch, placing it just behind Opus 4.8 and Fable 5 while using far more turns than Sonnet 4.6. Lower token pricing did not make agentic tasks cheaper, and some finance benchmarks still triggered refusals.
Fable 5 users report Opus 4.8 fallbacks, refusals, and $321 sessions
Ramp introduces PorTAL with half-cost LoRA porting across Qwen and Gemma models
Google releases Nano Banana 2 Lite and Gemini Omni Flash
Hermes Agent updates web extraction with 60x faster reads and 49x lower cost
Briefs forJuly 3
Top storiesthis week
Cognition launches Devin Fusion with mid-session routing and 35% lower Fable-class cost
Cognition launched Devin Fusion, a hybrid coding harness that reroutes work mid-task and says it cuts Fable-class cost by 35%. Use it when upfront routing misses late complexity; the router can re-evaluate after investigation starts.
Codex fixes usage overcounting with one extra banked reset and auto-review rollback
A day after Codex reset limits for weekend drain reports, OpenAI said auto-review, duplicate background suggestions, and retry behavior were compounding usage and issued another full reset. Users also get one extra reset credit within 24 hours while reporting and scheduling fixes roll out.
Codex resets all usage limits as OpenAI investigates weekend drain reports
Two days after OpenAI said it had fixed Codex quota drain tied to fraud overflagging, the team opened a Sunday war room for fresh drain reports and issued a hard reset of user limits. The incident matters because background usage and reset rules were still opaque during long-running agent work.
Daily AI Digest
Get the best stories delivered
to your inbox